© 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. 40218
    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
    track
    -0.63
     track
    -0.56
    _track
    -0.52
     Track
    -0.51
    Track
    -0.51
    -track
    -0.47
    (track
    -0.47
    .track
    -0.46
     tracks
    -0.45
    TRACK
    -0.44
    POSITIVE LOGITS
    è¿Ľä¸ĢæŃ¥
    0.42
     further
    0.42
     Further
    0.35
     intersects
    0.33
    Further
    0.33
    éĢ²ä¸ĢæŃ¥
    0.31
    å°Ĩè¿Ľä¸ĢæŃ¥
    0.30
     crosses
    0.28
    磶
    0.27
     prism
    0.26
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.