© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51465
    Prev
    Next
    INDEX
    Explanations

    effort into

    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
    ocs
    -0.09
    åħ¸
    -0.09
    èĩªå·±
    -0.08
    è¶³å¤Ł
    -0.08
    裾
    -0.08
    ÑĩаÑĤ
    -0.08
    éĹ¼
    -0.08
    æķ£åıij
    -0.08
    ä¸ĵä¸ļ人士
    -0.08
    çī¢åĽº
    -0.08
    POSITIVE LOGITS
     Reviewed
    0.11
    ç¡®ä¿Ŀ
    0.10
    æIJı
    0.10
    çļĦ表æĥħ
    0.09
    æijĺ
    0.09
    è¿Ļä¸ĢåĪ»
    0.09
    æĬĵ好
    0.08
    å½ĵãģŁãĤĬ
    0.08
    /power
    0.08
    enic
    0.08
    Activations Density 0.019%

    No Known Activations