© 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. 31-TRANSCODER-HP
    7. 18854
    Prev
    Next
    INDEX
    Explanations

    claim

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dol
    -0.29
    efully
    -0.28
    éĢļ
    -0.26
    ofi
    -0.26
    å¾Ħ
    -0.25
    éĵ
    -0.25
    è¦ģæ±Ĥ
    -0.24
     Publishers
    -0.24
     auprès
    -0.24
     Pass
    -0.24
    POSITIVE LOGITS
     left
    0.37
     worth
    0.31
    left
    0.28
    holding
    0.28
     judge
    0.28
     Left
    0.28
    _left
    0.27
    è¿Ļä¸Ģå¹´
    0.27
    å·¦
    0.27
    .left
    0.26
    Activations Density 0.380%

    No Known Activations