© 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. 128938
    Prev
    Next
    INDEX
    Explanations

    Corrupted/unusual text characters

    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
    alice
    -0.30
    èĵij
    -0.28
    boro
    -0.28
    forth
    -0.27
    æĬ¥åºŁ
    -0.26
    æĸ°å¾ģç¨ĭ
    -0.24
    澤
    -0.24
    à¸Ķาร
    -0.24
    orp
    -0.24
    fast
    -0.24
    POSITIVE LOGITS
    -shadow
    0.28
     shadow
    0.25
    浪
    0.24
    æĺ¯ä½ł
    0.24
    åŃª
    0.23
    _since
    0.23
    Assigned
    0.23
    åħ¶æīĢ
    0.23
    ohn
    0.23
     hottest
    0.22
    Activations Density 0.172%

    No Known Activations