© 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. 131222
    Prev
    Next
    INDEX
    Explanations

    but

    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
     After
    -0.36
    After
    -0.34
    æĪIJè´¥
    -0.32
     Successfully
    -0.31
     after
    -0.30
    .After
    -0.30
    _after
    -0.29
    èµĽåIJİ
    -0.29
     ÑĢезÑĥлÑĮÑĤаÑĤ
    -0.29
    ç»ĵå±Ģ
    -0.28
    POSITIVE LOGITS
    ä¿®å¤į
    0.29
    -current
    0.29
     existing
    0.28
    çľ¼ä¸Ń
    0.27
    åŃĺåľ¨äºİ
    0.27
     current
    0.27
     currentState
    0.26
    å½ĵåīį
    0.26
    IfExists
    0.26
    aware
    0.26
    Activations Density 0.002%

    No Known Activations