© 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. 30-TRANSCODER-HP
    7. 95935
    Prev
    Next
    INDEX
    Explanations

    code and file information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illian
    -0.28
    UDA
    -0.27
     ventil
    -0.27
    æĦı大
    -0.27
     bid
    -0.25
    olid
    -0.25
     Bid
    -0.25
    åĿĢ
    -0.24
    éľĩèį¡
    -0.24
    ä¸ĩéĩĮ
    -0.24
    POSITIVE LOGITS
    eyJ
    0.31
    çĥŃå¿ĥ
    0.29
    ä¸ĭæ²ī
    0.29
    gings
    0.28
    Top
    0.28
     top
    0.27
    _top
    0.26
    ETA
    0.26
    顶端
    0.26
     Slug
    0.26
    Activations Density 0.002%

    No Known Activations