© 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. 19-TRANSCODER-HP
    7. 7859
    Prev
    Next
    INDEX
    Explanations

    Code related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Trail
    -0.26
    miÅŁ
    -0.26
    uell
    -0.24
    dem
    -0.24
    éĻIJæľŁ
    -0.24
     zap
    -0.24
    utsch
    -0.23
     dem
    -0.23
     [[]
    -0.23
    çĥŃæĴŃ
    -0.23
    POSITIVE LOGITS
    REN
    0.28
    æĥħåł±
    0.27
    åĮĸè¿Ľç¨ĭ
    0.26
    ãĤīãģĦ
    0.25
    esses
    0.25
    ä¿¡æģ¯
    0.25
    ODY
    0.24
    lap
    0.24
    _information
    0.24
    ä¿¡æģ¯æľįåĬ¡
    0.24
    Activations Density 0.020%

    No Known Activations