© 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. 97278
    Prev
    Next
    INDEX
    Explanations

    First-person questions

    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
    羡
    -0.32
    临
    -0.27
     icing
    -0.26
    bestos
    -0.26
    asename
    -0.26
    çķ¥
    -0.26
    æľį
    -0.25
     alarmed
    -0.24
    åı¦ä¸Ģ
    -0.24
    åŀĭ
    -0.24
    POSITIVE LOGITS
    éĶĻ
    0.31
    éĮ¯
    0.30
     am
    0.28
    çľģæķĻèĤ²
    0.28
    ä¸ĵä¸ļçļĦ
    0.27
    çºł
    0.26
    ãģĬãģĭ
    0.26
     correction
    0.26
    åı¯èĥ½åŃĺåľ¨
    0.25
     mistaken
    0.25
    Activations Density 0.176%

    No Known Activations