© 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. 64270
    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
    .mix
    -0.28
    交åıī
    -0.27
     bows
    -0.25
    findFirst
    -0.25
    leigh
    -0.24
     Cross
    -0.24
    haft
    -0.24
     mixin
    -0.24
    lick
    -0.24
     MIS
    -0.24
    POSITIVE LOGITS
    éĴ¢æĿ¿
    0.28
    iera
    0.28
    èĵ¼
    0.27
     деле
    0.26
    衽
    0.26
    èī²ç´ł
    0.25
    京éĥ½
    0.24
    çĺ°
    0.24
    éķī
    0.24
    ä¸ĭæĿ¥çļĦ
    0.24
    Activations Density 31.658%

    No Known Activations

    This feature has no known activations.