© 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. 29997
    Prev
    Next
    INDEX
    Explanations

    ven

    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
    -old
    -0.26
    ced
    -0.26
    漫
    -0.26
    angkan
    -0.25
    åĨį说
    -0.25
    ,out
    -0.25
    æĢ»æĶ¶åħ¥
    -0.25
     surrounding
    -0.24
    mach
    -0.24
     numeral
    -0.24
    POSITIVE LOGITS
    peare
    0.30
    _ctor
    0.28
    ?option
    0.27
    fst
    0.27
     Cheer
    0.26
     forwards
    0.26
     vids
    0.26
     unserialize
    0.26
    è¾ĺ
    0.26
     clears
    0.25
    Activations Density 1.571%

    No Known Activations