© 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. 10160
    Prev
    Next
    INDEX
    Explanations

    vertebrae, vertebrate, ecteinascidin, Authors, chord, trace, stack trace

    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
    èĪŀ
    -0.09
    婵
    -0.09
    åģī
    -0.08
    å¤ı
    -0.08
    edy
    -0.08
    çļĦå±ĢéĿ¢
    -0.08
    沩
    -0.08
    æ§
    -0.08
    olv
    -0.08
    æĻļæĬ¥
    -0.08
    POSITIVE LOGITS
    åı£å²¸
    0.10
    æĬĵä½ı
    0.09
    èĦĸåŃIJ
    0.09
    æĮ£
    0.09
    .setColumns
    0.09
    æĮĤçĿĢ
    0.09
    è±ķ
    0.08
    æĮĤéĴ©
    0.08
    Beh
    0.08
    åĮ¹
    0.08
    Activations Density 0.142%

    No Known Activations