© 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. 111216
    Prev
    Next
    INDEX
    Explanations

    Code layouts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     colum
    -0.32
     columns
    -0.29
     Colum
    -0.28
    Ñīий
    -0.27
    columns
    -0.26
    çļĦåľ°
    -0.26
     Mont
    -0.26
    utive
    -0.25
     fi
    -0.25
    趾
    -0.25
    POSITIVE LOGITS
    管çIJĨå·¥ä½ľ
    0.26
    die
    0.26
    ä¸İæѤ
    0.25
    æĬ¥è®°èĢħ
    0.25
    ä¸Ģå°ı
    0.25
     plag
    0.24
    å¹´ä¸ŃåĽ½
    0.24
     erw
    0.24
    dh
    0.24
    èĢģ乡
    0.24
    Activations Density 0.024%

    No Known Activations