© 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. 19583
    Prev
    Next
    INDEX
    Explanations

    recurring events

    np_max-act-logits · gemini-2.0-flash
    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
    Not in Any Lists

    No Comments

    Negative Logits
     afr
    -0.25
    æľīèī²
    -0.25
     vacant
    -0.25
    é©°
    -0.24
    thur
    -0.23
    KeyId
    -0.23
    fce
    -0.23
    ç§ĺ书éķ¿
    -0.23
    .masks
    -0.23
    åħ³ç¨İ
    -0.23
    POSITIVE LOGITS
     about
    0.29
    About
    0.29
    åħ³äºİ
    0.28
    _FLASH
    0.26
    AD
    0.26
    ändig
    0.26
    XD
    0.26
    彩
    0.26
    å¤ļå¹´
    0.25
    åħ«åŃĹ
    0.25
    Activations Density 0.423%

    No Known Activations