© 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. 87058
    Prev
    Next
    INDEX
    Explanations

    further

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åįģ足
    -0.26
     simult
    -0.26
    ä¸Ĭç½ij
    -0.26
    èĴľ
    -0.25
    æ±ŁåĮº
    -0.25
     metric
    -0.24
    metric
    -0.24
    丰å¯Į
    -0.24
    æľŁæľĽ
    -0.24
     Metric
    -0.24
    POSITIVE LOGITS
     wors
    0.29
     Provid
    0.28
     dá»ĭ
    0.28
    ä¸įåĪ©äºİ
    0.27
    leurs
    0.26
    illo
    0.26
    Fuse
    0.25
    åĩºåħ¥
    0.25
    lov
    0.25
     unsuccessfully
    0.25
    Activations Density 0.006%

    No Known Activations