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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 150316
    Prev
    Next
    INDEX
    Explanations

    IV

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enty
    -0.27
    æĿ¥çĶµ
    -0.27
    /manage
    -0.27
    éĽĨåĽ¢èĤ¡ä»½
    -0.25
    çĸ¾
    -0.25
    studio
    -0.24
    ije
    -0.24
    bsites
    -0.23
    ãģĤãĤĬãģĮãģ¨ãģĨ
    -0.23
     recruit
    -0.23
    POSITIVE LOGITS
    (es
    0.27
    åİŁæĸĩåľ°åĿĢ
    0.25
    à¤ł
    0.25
    涯
    0.24
     impression
    0.24
    åŃķæľŁ
    0.23
    lies
    0.23
    ï¼Ĵ
    0.23
     just
    0.23
     uncon
    0.23
    Activations Density 1.069%

    No Known Activations