© 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. 24-TRANSCODER-HP
    7. 149320
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èĮĥåĽ´
    -0.28
    æ³Į
    -0.27
    åĨį说
    -0.27
    acies
    -0.26
    istra
    -0.26
    TemplateName
    -0.26
     nhi
    -0.26
    пÑĥÑģ
    -0.25
    iesta
    -0.25
    ’Ãł
    -0.25
    POSITIVE LOGITS
     contr
    0.25
    oli
    0.23
     bip
    0.23
    vi
    0.23
    lam
    0.23
     phó
    0.23
     Relax
    0.23
    isure
    0.23
    imir
    0.23
    /layouts
    0.22
    Activations Density 0.154%

    No Known Activations

    This feature has no known activations.