© 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. 86733
    Prev
    Next
    INDEX
    Explanations

    Unusual characters or foreign language

    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
    ç»ıå¼Ģ
    -0.29
    ä¸įåı¯æĢĿ
    -0.27
    iments
    -0.27
    lain
    -0.26
    æĭĹ
    -0.26
    æ¿Ĥ
    -0.26
    psz
    -0.26
    è²Į
    -0.26
    lemn
    -0.25
    ä»ij
    -0.25
    POSITIVE LOGITS
    -free
    0.27
    He
    0.27
    ãģĵãģĨ
    0.26
     G
    0.25
    éľŀ
    0.25
    ensi
    0.24
     necessary
    0.24
    åĩıåħį
    0.24
     He
    0.24
     '|
    0.24
    Activations Density 0.029%

    No Known Activations