© 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. 51933
    Prev
    Next
    INDEX
    Explanations

    before or after

    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
    å¡Į
    -0.09
    гаÑĢ
    -0.08
    éĽģ
    -0.08
     маÑģÑĤ
    -0.08
    æĪijèĩªå·±
    -0.08
    çĶ¨äºº
    -0.08
    å¾ĹçĽĬ
    -0.08
    obia
    -0.08
    à¸ķาย
    -0.08
    enty
    -0.08
    POSITIVE LOGITS
    娥
    0.09
    çĥŃæĴŃ
    0.09
    溺
    0.09
     меÑĢ
    0.09
    éĢĭ
    0.09
    ä¸ºè¿Ľä¸ĢæŃ¥
    0.09
    æİ·
    0.09
    åģ¥åº·æĪIJéķ¿
    0.09
    ARY
    0.08
    è¿Ļ段æŶéĹ´
    0.08
    Activations Density 0.046%

    No Known Activations