© 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. 20254
    Prev
    Next
    INDEX
    Explanations

    great followed by desirable features

    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
    忽
    -0.10
    ync
    -0.09
    åľ°éĿ¢
    -0.09
    çĶ¨æĪ·æıIJä¾Ľ
    -0.08
    æŃ£æĸĩ
    -0.08
    åľ¨é¦Ļ港
    -0.08
    è¾ŀ
    -0.08
    çijľ
    -0.08
    TÃľ
    -0.08
    ç¥ľ
    -0.08
    POSITIVE LOGITS
    å°ıä¼Ļ
    0.09
    èĩªè´¸
    0.09
    opp
    0.08
    æ¸ħåĩī
    0.08
    haft
    0.08
     forecast
    0.08
    emma
    0.08
    æľī两个
    0.08
    好çİ©
    0.08
    à¹Ģล
    0.08
    Activations Density 0.027%

    No Known Activations