© 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. 39860
    Prev
    Next
    INDEX
    Explanations

    news publications and media

    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
    祸
    -0.11
    çŃ·
    -0.11
    è¿Ļ对
    -0.10
     recap
    -0.09
    onga
    -0.09
    帽
    -0.09
     pisc
    -0.09
    红楼
    -0.09
    åĶ®
    -0.09
    =#{
    -0.09
    POSITIVE LOGITS
    ç´§æī£
    0.09
    çī¢
    0.09
    tele
    0.08
    æī§æĦı
    0.08
    èĢģçĻ¾å§ĵ
    0.08
    åŃº
    0.08
    毫ä¸į
    0.08
    rade
    0.08
    åħļé£İ
    0.08
    åį¦
    0.07
    Activations Density 0.065%

    No Known Activations