© 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. 19-TRANSCODER-HP
    7. 9321
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     __________________↵↵
    -0.29
    vince
    -0.27
    icult
    -0.26
    lobber
    -0.25
    -net
    -0.25
    -du
    -0.25
    chest
    -0.25
    vic
    -0.25
    èĨ
    -0.25
    stuff
    -0.24
    POSITIVE LOGITS
    /company
    0.27
    ä»ĸåıĪ
    0.26
    ç§ģ
    0.26
     communities
    0.25
     Begins
    0.25
    :on
    0.24
    对åħ¬åı¸
    0.24
    SYM
    0.24
    omen
    0.24
     compañ
    0.23
    Activations Density 0.132%

    No Known Activations

    This feature has no known activations.