© 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. 64246
    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
    hue
    -0.32
    æ¦ľ
    -0.29
    对åѦçĶŁ
    -0.27
    jang
    -0.27
    çī¹èī²çļĦ
    -0.27
    åĭ¢
    -0.27
    æĽ²æĬĺ
    -0.26
    increments
    -0.26
    Contours
    -0.25
    æļ´éĽ¨
    -0.25
    POSITIVE LOGITS
     act
    0.30
     mitt
    0.27
    åIJ¯åĬ¨
    0.26
    å¥ij约
    0.25
     Mitt
    0.25
     term
    0.25
    åį¸
    0.24
    Ex
    0.24
     Ex
    0.24
    appers
    0.24
    Activations Density 1.814%

    No Known Activations

    This feature has no known activations.