© 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. 107030
    Prev
    Next
    INDEX
    Explanations

    Code, machine learning, animals

    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
    dde
    -0.25
     solidity
    -0.24
    ,U
    -0.24
    è¿Ļåıªæĺ¯
    -0.24
    (___
    -0.24
    /tcp
    -0.23
    å·¡åĽŀ
    -0.23
    tm
    -0.23
    æĹ¢çĦ¶
    -0.23
    çĶ²éĨĽ
    -0.23
    POSITIVE LOGITS
    stitution
    0.26
    çķĮ第ä¸Ģ
    0.26
    lice
    0.25
    ype
    0.24
    etc
    0.24
    isan
    0.24
    \P
    0.24
     incor
    0.24
    jsc
    0.24
     etc
    0.23
    Activations Density 5.956%

    No Known Activations