© 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. 19-TRANSCODER-HP
    7. 9319
    Prev
    Next
    INDEX
    Explanations

    nutrition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -corner
    -0.27
    ä½łçŁ¥éģĵ
    -0.26
    ä½łåĸľæ¬¢
    -0.25
     vero
    -0.24
    æĪijåĴĮ
    -0.24
     straight
    -0.23
    å¿ħãģļ
    -0.23
    Sketch
    -0.23
    erview
    -0.23
    æĪijè¦ģ
    -0.22
    POSITIVE LOGITS
    hma
    0.27
    _manage
    0.26
    iest
    0.26
    ä¸ĭä¸Ģ代
    0.26
    mates
    0.24
    META
    0.24
    ÑģÑĤвÑĥ
    0.24
    ening
    0.24
    åIJĦå¼Ĥ
    0.24
    ful
    0.23
    Activations Density 3.027%

    No Known Activations