© 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. 37396
    Prev
    Next
    INDEX
    Explanations

    good or great outcomes

    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
    ACHI
    -0.09
    æ±´
    -0.09
    äº§åľ°
    -0.09
    褫
    -0.08
    æij¸ç´¢
    -0.08
    "\↵
    -0.08
    ads
    -0.08
    .slim
    -0.08
    åľ¨å½ĵåľ°
    -0.08
    phas
    -0.08
    POSITIVE LOGITS
    æIJŀ好
    0.09
    强迫
    0.09
    ä¸įåħį
    0.09
    çĻ£
    0.09
    å¢ĥåĨħ
    0.09
    åºķæ°Ķ
    0.08
    urst
    0.08
    å¿«æĬ¥
    0.08
    éĮ¾
    0.08
    å·¥ç¨ĭè´¨éĩı
    0.08
    Activations Density 0.046%

    No Known Activations