© 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. 86823
    Prev
    Next
    INDEX
    Explanations

    Materials/technical specifications

    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
    oop
    -0.29
    æĺ¯ä½ł
    -0.26
    -metadata
    -0.25
    ç«Ļç«ĭ
    -0.24
     surve
    -0.24
     chu
    -0.23
    å½ķçĶ¨
    -0.23
    管çIJĨå±Ĥ
    -0.23
     rele
    -0.23
     rotations
    -0.23
    POSITIVE LOGITS
    ilogy
    0.26
     Köln
    0.25
    [V
    0.25
    دÙĨÙĬ
    0.25
    adol
    0.24
     minim
    0.24
    )V
    0.24
    åĿŃ
    0.24
    mine
    0.23
    _vel
    0.23
    Activations Density 0.064%

    No Known Activations