© 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. 89001
    Prev
    Next
    INDEX
    Explanations

    businesses and organizations

    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
    law
    -0.25
    个æĢ§
    -0.25
    ç¾İ
    -0.25
    äºİ
    -0.25
    ença
    -0.24
    æľŁ
    -0.24
    åģ¶
    -0.24
     initialState
    -0.24
    磩
    -0.24
     handed
    -0.24
    POSITIVE LOGITS
    andin
    0.31
    ä¸Ģè§Ĵ
    0.27
    )::
    0.26
    ãģŁãĤī
    0.25
     NSK
    0.24
    _Module
    0.23
    ATS
    0.23
    åį´è¢«
    0.23
    anything
    0.23
    INES
    0.23
    Activations Density 0.003%

    No Known Activations