© 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. 129128
    Prev
    Next
    INDEX
    Explanations

    proper/right

    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
    äºĭä¸ļ
    -0.33
    iard
    -0.28
    umpy
    -0.25
    imization
    -0.25
    éĿł
    -0.25
    otron
    -0.24
     cors
    -0.24
    oby
    -0.24
    asks
    -0.23
    otope
    -0.23
    POSITIVE LOGITS
    ç»Īäºİ
    0.30
     functioning
    0.29
    ongo
    0.27
    legg
    0.26
    æ¯Ķä¾ĭ
    0.25
    iete
    0.25
    placement
    0.25
     Ä°n
    0.25
    allocation
    0.25
     allocation
    0.25
    Activations Density 0.048%

    No Known Activations