© 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. 109222
    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
    è¾ĸ
    -0.28
    éľĪ
    -0.27
    æīĢå±ŀ
    -0.27
    æ´ĭ
    -0.26
    urn
    -0.26
    åŁĭ
    -0.25
    Len
    -0.25
    Kay
    -0.24
    ...
    -0.24
    let
    -0.24
    POSITIVE LOGITS
    estone
    0.30
    -neutral
    0.27
    tracts
    0.25
    neutral
    0.25
    -peer
    0.24
    âĢ¾
    0.24
    -unit
    0.24
    IJ
    0.24
    peer
    0.24
    æĴŀ
    0.23
    Activations Density 0.930%

    No Known Activations

    This feature has no known activations.