© 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. 32-TRANSCODER-HP
    7. 41138
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antages
    -0.27
     Ø¥ÙĦÙĬ
    -0.24
    èħĬ
    -0.24
    _REFERENCE
    -0.24
    urance
    -0.24
    åķľ
    -0.24
    **/↵↵
    -0.24
    onation
    -0.24
    ummer
    -0.22
     Ox
    -0.22
    POSITIVE LOGITS
    acente
    0.26
    aby
    0.26
    Bindable
    0.23
    æ³±
    0.23
    asive
    0.23
    æĥħ人
    0.23
     outpatient
    0.22
    èĩ¾
    0.22
    versions
    0.22
    RIA
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.