© 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. 40241
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    _disc
    -0.28
    oglob
    -0.26
    .tie
    -0.26
    .XR
    -0.25
    åļ¼
    -0.25
    Disc
    -0.25
    ä¸ĢéĹª
    -0.24
    xis
    -0.24
    å¸ĤæķĻèĤ²
    -0.24
    æĹ¢æľī
    -0.24
    POSITIVE LOGITS
    jsonp
    0.28
    urous
    0.26
     Stranger
    0.26
    大象
    0.26
     strange
    0.26
    çĨŁæĤī
    0.25
     reason
    0.24
     hơi
    0.24
    æĢ»ç»ĵ
    0.24
    [z
    0.24
    Activations Density 9.451%

    No Known Activations

    This feature has no known activations.