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. 120664
    Prev
    Next
    INDEX
    Explanations

    ::

    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
    peare
    -0.07
    elia
    -0.07
    海绵
    -0.07
     Pine
    -0.07
     Flutter
    -0.06
     neckline
    -0.06
    uet
    -0.06
    小米
    -0.06
     돌
    -0.06
     Players
    -0.06
    POSITIVE LOGITS
     �
    0.07
    ,opt
    0.07
     Ottoman
    0.07
     따른
    0.07
    scheduled
    0.07
     --------------------------------
    0.07
     accelerate
    0.07
    _transaksi
    0.06
     Later
    0.06
    liced
    0.06
    Activations Density 0.002%

    No Known Activations