© 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. 129005
    Prev
    Next
    INDEX
    Explanations

    Scanned documents and code

    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
    åĪ®
    -0.28
    æĥ³ä¸įåĪ°
    -0.27
    æŃª
    -0.25
    à¸ģว
    -0.25
    .li
    -0.24
    й
    -0.24
    enthal
    -0.24
    à¸ģล
    -0.24
    åį±
    -0.24
    xffff
    -0.24
    POSITIVE LOGITS
    ä¸īæľŁ
    0.29
    fdc
    0.28
    loth
    0.28
    帮æĪij
    0.27
     tertiary
    0.27
     instruct
    0.26
     forthcoming
    0.26
    媾
    0.26
    omed
    0.25
     бÑĥдÑĥ
    0.25
    Activations Density 0.002%

    No Known Activations