© 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. 107648
    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
    \č↵
    -0.28
     Va
    -0.27
    é¢Ĭ
    -0.27
    ç»Ī身
    -0.25
     Counts
    -0.25
    agency
    -0.25
     ADV
    -0.25
    çĵ·åĻ¨
    -0.24
     adv
    -0.24
     kick
    -0.24
    POSITIVE LOGITS
    ç½ij讯
    0.31
    åIJĮä»ģ
    0.26
    éĥ½æĺ¯éĿŀ常
    0.26
    åıĪ好
    0.25
    akens
    0.25
     sweating
    0.25
    Ļ¨
    0.25
     hitch
    0.25
    %S
    0.24
     fodder
    0.24
    Activations Density 43.169%

    No Known Activations

    This feature has no known activations.