© 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. 29578
    Prev
    Next
    INDEX
    Explanations

    bo

    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
    å®ī
    -0.28
     match
    -0.27
    åIJij举
    -0.24
    WEST
    -0.24
    .Lerp
    -0.24
    Match
    -0.24
     inst
    -0.24
    éļ¾
    -0.24
     Sachs
    -0.24
    _poll
    -0.24
    POSITIVE LOGITS
    èĭĹ
    0.25
    elper
    0.24
    代çIJĨ人
    0.24
    caret
    0.24
    _TYPEDEF
    0.24
    batim
    0.24
    rais
    0.24
    æ¼ĵ
    0.24
     ReturnType
    0.24
    aving
    0.23
    Activations Density 1.667%

    No Known Activations