© 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. 35-TRANSCODER-HP
    7. 39549
    Prev
    Next
    INDEX
    Explanations

    scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .']
    -0.34
    .',č↵
    -0.33
    .';↵
    -0.32
    .*/↵
    -0.31
    .";č↵
    -0.31
    .'.$
    -0.31
    .|
    -0.31
    .','
    -0.30
    .');č↵
    -0.30
    .).↵↵
    -0.30
    POSITIVE LOGITS
     extends
    0.35
    -short
    0.35
    -weight
    0.34
    -s
    0.33
    -sh
    0.32
    CT
    0.32
    -fed
    0.32
    ret
    0.31
    -
    0.31
    -R
    0.31
    Activations Density 8.073%

    No Known Activations