© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 75599
    Prev
    Next
    INDEX
    Explanations

    blog posts and questions

    np_max-act · gemini-2.0-flash

    Tokens that mark the assistant's turn/start of an assistant response (assistant-turn boundary).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jika
    -0.08
     slicing
    -0.08
    ◪
    -0.08
    =?",
    -0.07
    \Blueprint
    -0.07
     uncovered
    -0.07
    عزل
    -0.07
     QTableWidgetItem
    -0.07
    จอง
    -0.07
     araştırma
    -0.07
    POSITIVE LOGITS
    입
    0.07
     AUT
    0.07
    /tos
    0.07
     kwargs
    0.07
     accum
    0.07
     appar
    0.07
     ROW
    0.06
     linewidth
    0.06
    IBUT
    0.06
    .Random
    0.06
    Activations Density 0.286%

    No Known Activations