© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40142
    Prev
    Next
    INDEX
    Explanations

    very

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĸľæ¬¢
    -0.42
    ?
    -0.39
    éĢĤåIJĪ
    -0.34
    ï¼Ł
    -0.31
    好çļĦ
    -0.30
    éĿŀ常
    -0.30
    é«ĺ
    -0.29
    æĽ´éĢĤåIJĪ
    -0.29
    没æľīä»»ä½ķ
    -0.28
    åĸľæ¬¢åIJĥ
    -0.28
    POSITIVE LOGITS
    尽头
    0.27
    åľ¨åľ°ä¸Ĭ
    0.26
     newest
    0.25
     latest
    0.25
     wohl
    0.25
     Chop
    0.24
    .latest
    0.24
    -Version
    0.24
    /latest
    0.23
     real
    0.23
    Activations Density 21.412%

    No Known Activations