© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26438
    Prev
    Next
    INDEX
    Explanations

    semi hyphenated words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inine
    -0.09
    iness
    -0.09
    cis
    -0.08
     sonst
    -0.08
     Dah
    -0.08
    in
    -0.08
    ãģªãģĭãģªãģĭ
    -0.08
    zell
    -0.08
    dì
    -0.08
    ighth
    -0.08
    POSITIVE LOGITS
    ä¸¥æł¼çļĦ
    0.10
    ities
    0.10
    wares
    0.10
    æµĵåİļ
    0.09
    æĸ¯åŁº
    0.09
    çļĦæĪIJåĬŁ
    0.09
    cé
    0.09
    NEY
    0.09
    åħ¨èĥ½
    0.09
    ร
    0.09
    Activations Density 0.006%

    No Known Activations