© 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. 32721
    Prev
    Next
    INDEX
    Explanations

    copyright and protected works

    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¸įå¼Ģ
    -0.08
    å·¡èĪª
    -0.08
    ponent
    -0.08
    çĵ¦
    -0.08
     expend
    -0.07
    ov
    -0.07
     Cascade
    -0.07
    ovsky
    -0.07
     Casc
    -0.07
    æ¶Į
    -0.07
    POSITIVE LOGITS
    çļĦä½ľåĵģ
    0.11
    ä½ľåĵģ
    0.11
    å°ıå¾®
    0.10
    ä¸įç»ıæĦı
    0.10
     skl
    0.10
     sát
    0.10
    è¿·ä½ł
    0.10
    ä¼łåªĴ
    0.09
    åģļæĪIJ
    0.09
    åĻ«
    0.09
    Activations Density 0.053%

    No Known Activations