© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107304
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingleton
    -0.28
    調
    -0.27
     rooms
    -0.27
    æĪ¿éĹ´
    -0.27
    æ§Ł
    -0.26
    Rooms
    -0.26
    äºĭåĬ¡
    -0.26
    ogne
    -0.25
    (Location
    -0.25
    mor
    -0.25
    POSITIVE LOGITS
    icians
    0.24
     differential
    0.24
     Minute
    0.23
    -be
    0.23
    _OVERRIDE
    0.23
     Redskins
    0.23
     Sty
    0.23
    FETCH
    0.22
     franchise
    0.22
    åĬ²
    0.22
    Activations Density 0.952%

    No Known Activations

    This feature has no known activations.