© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6899
    Prev
    Next
    INDEX
    Explanations

    OCR/formatting artifacts

    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
    ãģĻãĤĭãģ®ãģĮ
    -0.28
     insure
    -0.27
    reich
    -0.25
     constitution
    -0.23
     mall
    -0.23
    utta
    -0.23
    atisch
    -0.23
    ypass
    -0.23
    _GAP
    -0.22
    owego
    -0.22
    POSITIVE LOGITS
     Cs
    0.25
    è¿Ń
    0.25
     Assigned
    0.24
    ?-
    0.24
    à¸ļà¸Ńà¸ģ
    0.24
    丢
    0.24
    丢äºĨ
    0.24
    åı¤èĢģ
    0.23
    Counter
    0.23
     auto
    0.23
    Activations Density 0.055%

    No Known Activations