© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22179
    Prev
    Next
    INDEX
    Explanations

    building entrance

    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
    大åѦæ¯ķä¸ļ
    -0.10
    èĤļ
    -0.09
    容纳
    -0.09
    åıªçŁ¥éģĵ
    -0.09
    eken
    -0.09
    åĪ°æľĢåIJİ
    -0.09
    åıįåĢĴ
    -0.08
    snippet
    -0.08
    家ä½ı
    -0.08
    åĿıäºĨ
    -0.08
    POSITIVE LOGITS
    æĹģ
    0.12
     Ùħباشرة
    0.11
    åIJ¦
    0.09
    è¾¹ç¼ĺ
    0.09
    为ä¸Ńå¿ĥ
    0.09
    éĻĦè¿ij
    0.09
    ä¸Ģéģĵ
    0.08
    ugins
    0.08
     Innoc
    0.08
    æľĿéĺ³
    0.08
    Activations Density 0.117%

    No Known Activations