© 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. 38515
    Prev
    Next
    INDEX
    Explanations

    matching or corresponding

    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
    eware
    -0.10
    ä¿ĺ
    -0.09
    	TokenName
    -0.09
    .Shared
    -0.09
    éĤ£ä½ł
    -0.09
    æļ´
    -0.09
     Quá»ijc
    -0.09
    orf
    -0.08
    ori
    -0.08
    çĮ¥
    -0.08
    POSITIVE LOGITS
    é½IJåħ¨
    0.12
    éħįå¥Ĺ
    0.10
    婵
    0.10
    ä¸įæĿ¥
    0.09
    ãĥIJãĥ³
    0.08
    ç¬ijèĦ¸
    0.08
    æIJŃæ¡£
    0.08
    ä¸įäºĨ
    0.08
    缸åºĶ
    0.08
    æĤ
    0.08
    Activations Density 0.028%

    No Known Activations