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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 59508
    Prev
    Next
    INDEX
    Explanations

    id

    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
     어떻게
    -0.08
     "../../../
    -0.07
     thuật
    -0.07
     proposé
    -0.07
    .centerX
    -0.07
    Ленин
    -0.07
    🚑
    -0.06
     części
    -0.06
    窥
    -0.06
    .REQUEST
    -0.06
    POSITIVE LOGITS
    wid
    0.08
    ]]
    0.07
     Pont
    0.07
     sab
    0.07
     workplace
    0.06
    iling
    0.06
     [#
    0.06
    ford
    0.06
    ())↵
    0.06
    _Email
    0.06
    Activations Density 0.000%

    No Known Activations