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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19-RESID-POST-AA
    11. 5304
    Prev
    Next
    INDEX
    Explanations

    technical question and answer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝜋
    -0.08
    ambil
    -0.07
     בתחום
    -0.07
    릎
    -0.07
     '">'
    -0.06
    胚
    -0.06
    rende
    -0.06
     pieniądze
    -0.06
    .beginTransaction
    -0.06
     concluded
    -0.06
    POSITIVE LOGITS
    neck
    0.08
    ither
    0.08
    _engine
    0.07
    共享
    0.07
    haven
    0.07
     MACHINE
    0.07
    поль
    0.07
    herits
    0.07
     Cow
    0.07
    _MODEL
    0.07
    Activations Density 0.062%

    No Known Activations