© 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. 31-TRANSCODER-HP
    7. 17815
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     NG
    -0.28
    åħ¬æĬ¥
    -0.27
    Probe
    -0.25
    ANI
    -0.25
    èµŁ
    -0.25
    .restore
    -0.24
    è¿Ļ个è¯į
    -0.24
    Ĭ¶æĢģ
    -0.24
     schön
    -0.24
    iverse
    -0.23
    POSITIVE LOGITS
    lu
    0.26
    .jupiter
    0.25
    еÑģÑĤв
    0.25
    æĹ¶æľŁ
    0.24
    æĺ¾çİ°
    0.24
    react
    0.24
     pla
    0.23
    æŁ¥éĺħ
    0.23
    ellant
    0.23
     inputFile
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.