© 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. 30931
    Prev
    Next
    INDEX
    Explanations

    49ers

    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
    SPORT
    -0.10
    彧
    -0.10
    NonQuery
    -0.10
    ROT
    -0.10
    è¿©
    -0.09
    stamp
    -0.09
     Geoff
    -0.09
    .EN
    -0.09
    stock
    -0.09
    ÑĢей
    -0.09
    POSITIVE LOGITS
    ulls
    0.09
    æĺĶ
    0.08
     Nom
    0.08
    å½¼
    0.08
    nom
    0.08
     nom
    0.08
    ç«ĭä½ĵ
    0.08
    è¦ģçŁ¥éģĵ
    0.07
    iew
    0.07
    thon
    0.07
    Activations Density 0.003%

    No Known Activations