© 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. 36492
    Prev
    Next
    INDEX
    Explanations

    -fold, avenues, fronts, facet

    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
    æĹ¶ä»£ä¸ŃåĽ½
    -0.08
    ucker
    -0.08
    ä¸įåĪĨ
    -0.08
    -checkbox
    -0.08
    èĻŀ
    -0.08
    æݼ
    -0.08
     Sach
    -0.08
    cps
    -0.08
    ÑĪе
    -0.08
    èĻ
    -0.08
    POSITIVE LOGITS
    ged
    0.12
    å¼ĢèĬ±
    0.10
    ç¨įç¨į
    0.10
    bars
    0.09
    å¦ĤæĦı
    0.09
    çĻ¸
    0.09
    alse
    0.09
    åıijå±ķä¸Ń
    0.09
    åķĨæľº
    0.08
    Ļ¶
    0.08
    Activations Density 0.017%

    No Known Activations