© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8431
    Prev
    Next
    INDEX
    Explanations

    per day, week, or year

    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
    éĢ¼è¿ij
    -0.09
    çŁ¥éģĵäºĨ
    -0.09
    obo
    -0.09
    çĪ·
    -0.09
    åľ¨ä»ĸ
    -0.08
    çªģçł´åı£
    -0.08
    6
    -0.08
     ба
    -0.08
     Sac
    -0.08
    ÑĢак
    -0.08
    POSITIVE LOGITS
    ä¸Ģ天
    0.13
    ä¸Ģå¹´
    0.11
    ä¸ĢæĹ¥
    0.11
     day
    0.11
     днÑı
    0.10
     week
    0.10
    EEK
    0.10
    week
    0.10
    å¤ļä¹Ī
    0.10
    èĤīä½ĵ
    0.10
    Activations Density 0.074%

    No Known Activations