© 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. 9509
    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
    Negative Logits
     cle
    -0.30
    æĸ½
    -0.28
    gments
    -0.27
    TM
    -0.26
    option
    -0.26
    åIJī
    -0.26
    çĶµå½±èĬĤ
    -0.25
    inst
    -0.25
    åij½
    -0.24
    sett
    -0.24
    POSITIVE LOGITS
    åŃ
    0.26
    LoginForm
    0.25
    豺
    0.25
    ALK
    0.25
    @endif
    0.24
    被åĪĹåħ¥
    0.24
    人éĢī
    0.24
    æµİ
    0.24
    é¾Ľ
    0.23
    AutoSize
    0.23
    Activations Density 0.187%

    No Known Activations

    This feature has no known activations.