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

    Neuronpedia

    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. 65627
    Prev
    Next
    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash
    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
    _EXIT
    -0.08
    -=
    -0.07
    (ps
    -0.07
    maintenance
    -0.07
    卓
    -0.06
    prises
    -0.06
    .transitions
    -0.06
    疼痛
    -0.06
    (CG
    -0.06
    .Tool
    -0.06
    POSITIVE LOGITS
     Lamb
    0.07
    etections
    0.07
     Nar
    0.07
     kur
    0.06
     tienen
    0.06
     Elena
    0.06
    王某
    0.06
    عباد
    0.06
    远离
    0.06
    뭍
    0.06
    Activations Density 0.066%

    No Known Activations