© 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. 23094
    Prev
    Next
    INDEX
    Explanations

    licking, hands, drinking, urine

    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
    éĵ¡
    -0.10
    翳
    -0.09
    åĬłå·¥
    -0.09
    èijĨ
    -0.08
    å·®è·Ŀ
    -0.08
    çIJĽ
    -0.08
    é«ĺè´¨éĩı
    -0.08
    æĸŃ
    -0.08
    ä¿Ĺ称
    -0.08
    edin
    -0.08
    POSITIVE LOGITS
    èĪĶ
    0.13
    åIJ®
    0.12
    èĪIJ
    0.11
     licking
    0.10
    åķĦ
    0.10
    汤
    0.09
    åĴĤ
    0.09
    åĶ®åIJİ
    0.09
    干线
    0.09
    lear
    0.09
    Activations Density 0.045%

    No Known Activations