© 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. 8115
    Prev
    Next
    INDEX
    Explanations

    fact

    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
    eval
    -0.08
    влечен
    -0.07
    Verify
    -0.07
    以后
    -0.07
    clidean
    -0.07
     долг
    -0.07
    广大市民
    -0.06
    ден
    -0.06
    Extensions
    -0.06
    .search
    -0.06
    POSITIVE LOGITS
    趔
    0.07
     JSBracketAccess
    0.07
    忭
    0.07
     brib
    0.07
    Cab
    0.07
    (stack
    0.07
    仅仅是
    0.07
    _FT
    0.07
     kad
    0.07
    队伍
    0.06
    Activations Density 0.000%

    No Known Activations