© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18516
    Prev
    Next
    INDEX
    Explanations

    conversation

    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
    çļĦçľ¼çĿĽ
    -0.10
    å¼Ģ
    -0.09
    æ¹Ķ
    -0.09
    çĹ¼
    -0.09
    ãģįãģ£
    -0.08
    è·Łè¸ª
    -0.08
    utr
    -0.08
    æ°ĹãģĮ
    -0.08
    åĩī
    -0.08
    å¼Ģ头
    -0.08
    POSITIVE LOGITS
    èĬĻ
    0.12
    åľ¨æĹ¥æľ¬
    0.12
    wig
    0.11
    æ·±åİļçļĦ
    0.10
    西æ´ĭ
    0.10
    é²·
    0.09
    çĶº
    0.09
     japan
    0.09
    æħĬ
    0.09
    大å¹ħæıIJåįĩ
    0.09
    Activations Density 0.122%

    No Known Activations