© 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. 9-TRANSCODER-HP
    7. 29495
    Prev
    Next
    INDEX
    Explanations

    describing, defining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $.
    -0.29
    lest
    -0.26
    åģļèµ·
    -0.25
    æ®Ĭ
    -0.25
    .Rad
    -0.25
    åİļéĩį
    -0.25
    '].$
    -0.24
    ymes
    -0.24
     win
    -0.23
     Vince
    -0.23
    POSITIVE LOGITS
    éĹ¨æ§Ľ
    0.29
    ynchronously
    0.28
     Kirst
    0.26
    ä¸įåŃķ
    0.26
    ár
    0.25
    _Char
    0.25
    essed
    0.24
    breaking
    0.24
    AndWait
    0.24
    _datasets
    0.24
    Activations Density 0.758%

    No Known Activations