© 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. 29681
    Prev
    Next
    INDEX
    Explanations

    being

    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
    åĩ»
    -0.26
     shut
    -0.25
    æľīæĦı
    -0.25
    _slow
    -0.25
    ourd
    -0.25
    æĵĬ
    -0.24
    COD
    -0.24
    Cont
    -0.24
    ayas
    -0.24
    .Cascade
    -0.23
    POSITIVE LOGITS
     subscribed
    0.28
    OfWork
    0.26
    对æĪij说
    0.26
    unan
    0.25
    resses
    0.25
    insic
    0.25
    注æĺİæĿ¥æºIJ
    0.25
    infer
    0.24
    olist
    0.24
    ืà¹Ī
    0.24
    Activations Density 4.464%

    No Known Activations