© 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. 31-TRANSCODER-HP
    7. 19681
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJī
    -0.29
    führt
    -0.26
     McCoy
    -0.26
    å±ķä½į
    -0.25
    ync
    -0.25
    landing
    -0.24
    cab
    -0.24
    kip
    -0.24
    dex
    -0.24
    daf
    -0.24
    POSITIVE LOGITS
     timeouts
    0.27
    åĦŁ
    0.26
    æŶéĹ´ä¸º
    0.26
    bei
    0.25
    itim
    0.25
    emarks
    0.24
    à¸Ńม
    0.24
    åĿ»
    0.24
    ãĥĹãĥ¬
    0.24
    elfare
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.