© 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. 22-TRANSCODER-HP
    7. 97147
    Prev
    Next
    INDEX
    Explanations

    every

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    LBL
    -0.29
    ins
    -0.27
    ëĿ½
    -0.26
     spoiled
    -0.25
    æĭĸæ¬ł
    -0.24
    irma
    -0.24
    ,W
    -0.24
    ä»ĵ
    -0.23
    å¤©åľ°
    -0.23
     Err
    -0.23
    POSITIVE LOGITS
     statistic
    0.30
    ptest
    0.27
    ersive
    0.26
    atform
    0.26
    HashCode
    0.26
    è¿Ļæī¹
    0.25
    æĹłéļľç¢į
    0.25
    .addEdge
    0.24
    ôme
    0.24
    acus
    0.24
    Activations Density 0.015%

    No Known Activations