© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142483
    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
    æ´½
    -0.34
    EndElement
    -0.26
    èħĨ
    -0.25
    sense
    -0.24
    è¿«ä¸įåıĬå¾ħ
    -0.24
     puff
    -0.24
    è¾ħåĬ©
    -0.24
    鸽
    -0.24
    omm
    -0.24
    åħ°èĬ±
    -0.24
    POSITIVE LOGITS
    anders
    0.26
    ublic
    0.26
    çĶ¨åĬĽ
    0.26
    <!--[
    0.25
    unders
    0.25
    mong
    0.25
    ä¸įåIJĮçļĦ
    0.24
     brut
    0.24
    Brad
    0.24
    伦æķ¦
    0.24
    Activations Density 1.794%

    No Known Activations

    This feature has no known activations.