Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 48747
    Prev
    Next
    INDEX
    Explanations

    either

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jm
    -0.08
    asons
    -0.07
    <Task
    -0.07
     בן
    -0.06
    ุ
    -0.06
    <<<<<<<<
    -0.06
    takes
    -0.06
     thats
    -0.06
    ז
    -0.06
    (log
    -0.06
    POSITIVE LOGITS
     drifted
    0.07
    暢
    0.07
     Ell
    0.07
     Panel
    0.07
     airy
    0.06
     крови
    0.06
     equitable
    0.06
    IGATION
    0.06
    走下去
    0.06
     Search
    0.06
    Activations Density 0.004%

    No Known Activations