© 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. 20-TRANSCODER-HP
    7. 130229
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹Łä¸į
    -0.28
    缮æłĩä»»åĬ¡
    -0.26
    paged
    -0.26
    ç»İ
    -0.25
    解æŀIJ
    -0.25
     unp
    -0.24
    ä¹Łæ¯Ķè¾ĥ
    -0.24
     contest
    -0.24
     stability
    -0.23
     GN
    -0.23
    POSITIVE LOGITS
    .bp
    0.26
    ecided
    0.26
     worden
    0.25
    身ä½ĵåģ¥åº·
    0.25
    itution
    0.24
     Jenkins
    0.24
    å®ĥ们
    0.24
    ;line
    0.23
    uelle
    0.23
    cene
    0.23
    Activations Density 6.936%

    No Known Activations

    This feature has no known activations.