© 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. 11396
    Prev
    Next
    INDEX
    Explanations

    making music

    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
    ä¸Ģ对
    -0.10
    她说
    -0.09
    ıkl
    -0.09
    åŁ
    -0.09
    æŀ¶åŃIJ
    -0.08
    aghan
    -0.08
    iah
    -0.08
     Lit
    -0.08
    åIJĮæľŁ
    -0.08
    çݯèĬĤ
    -0.08
    POSITIVE LOGITS
    ä½ľåĵģ
    0.14
    åĪ¶ä½ľ
    0.13
    çļĦä½ľåĵģ
    0.12
    è£½ä½ľ
    0.12
    åĪĽä½ľ
    0.12
    eln
    0.10
    ãĤĴä½ľãģ£ãģ¦
    0.09
    åīµä½ľ
    0.09
     ìŀijíĴĪ
    0.09
    ä¾Ľå¤§å®¶
    0.09
    Activations Density 0.080%

    No Known Activations