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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 71008
    Prev
    Next
    INDEX
    Explanations

    Academic publications

    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
    même
    -0.07
    .OutputStream
    -0.07
    ledge
    -0.07
    瓴
    -0.07
    itre
    -0.07
    mile
    -0.07
     systematically
    -0.07
    从未
    -0.07
    _SIMPLE
    -0.07
    商业
    -0.07
    POSITIVE LOGITS
    لحق
    0.09
    Saint
    0.08
     szcz
    0.07
    hl
    0.07
    _crop
    0.07
    (convert
    0.07
    eiß
    0.07
    (decimal
    0.07
    入侵
    0.07
     wur
    0.07
    Activations Density 0.009%

    No Known Activations