© 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. 20-TRANSCODER-HP
    7. 142215
    Prev
    Next
    INDEX
    Explanations

    second

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kers
    -0.25
    æģ°
    -0.25
    anded
    -0.25
    _cycles
    -0.24
     ('$
    -0.23
    /raw
    -0.23
    avage
    -0.23
     Parks
    -0.23
    Å¡e
    -0.23
    elier
    -0.23
    POSITIVE LOGITS
    èĩªæĿ¥
    0.32
    ç§ĥ
    0.28
    åı¦ä¸Ģæĸ¹éĿ¢
    0.28
    缸åħ³åĨħ容
    0.27
    è¾ĩ
    0.26
    inois
    0.26
    ãģ«éĸ¢ãģĹãģ¦
    0.25
    çļĦæł¹æľ¬
    0.25
    æĸ¹éĿ¢
    0.25
    contrib
    0.25
    Activations Density 62.323%

    No Known Activations