© 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. 58465
    Prev
    Next
    INDEX
    Explanations

    work together towards

    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
    èĶĵ延
    -0.09
    .cont
    -0.09
    ä¸įè´Ł
    -0.09
    å¼ķåıijäºĨ
    -0.09
     MASTER
    -0.09
    æĺ§
    -0.09
    adoo
    -0.09
    å¼ķåıij
    -0.09
    _mapped
    -0.08
    гон
    -0.08
    POSITIVE LOGITS
    åıĮæĸ¹
    0.12
    åħ±åIJĮ
    0.11
    åıĭ好
    0.10
    åĸĿæ°´
    0.09
    æ®ĵ
    0.09
    çļĦåIJĪä½ľ
    0.09
    åIJĪä½ľåħ³ç³»
    0.09
    笼
    0.09
    åIJĪä½ľåįıè®®
    0.09
    åĵªæĢķæĺ¯
    0.09
    Activations Density 0.044%

    No Known Activations