© 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. 63976
    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
    èĤļ
    -0.30
    èĥ¡èIJĿåįľ
    -0.27
    å®ļçĤ¹
    -0.27
    å®ŀäºĭ
    -0.25
    ÑģÑĤвенно
    -0.25
    æľīèĩªå·±çļĦ
    -0.24
    è¿ľæĻ¯
    -0.24
     flexGrow
    -0.24
    æĢĢæĬ±
    -0.24
    人ãĤĤ
    -0.24
    POSITIVE LOGITS
     Cos
    0.30
    lobs
    0.29
    è¡Į
    0.26
    åĪ¤
    0.26
    çīĻ
    0.25
     Suc
    0.25
     considering
    0.25
     Warn
    0.25
    аÑĤелÑĮ
    0.24
    åľ¨çº¿
    0.24
    Activations Density 10.313%

    No Known Activations

    This feature has no known activations.