© 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. 2745
    Prev
    Next
    INDEX
    Explanations

    gps, ABS, button, interior, Side, all, amed, go

    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
    å°ıä¼Ļä¼´
    -0.12
    çļĦ身ä½ĵ
    -0.11
     Spit
    -0.10
    è°Į
    -0.10
    积累äºĨ
    -0.10
    leta
    -0.10
    enta
    -0.10
    arde
    -0.10
    ENTA
    -0.10
     Publi
    -0.10
    POSITIVE LOGITS
    åĪĹåħ¥
    0.10
    缮
    0.10
    仲
    0.08
    åħ¬åŃIJ
    0.08
    wat
    0.08
    åĮħæĭ¬
    0.08
    æĿ²
    0.08
    .Sys
    0.08
     whip
    0.08
    该项
    0.08
    Activations Density 0.021%

    No Known Activations