© 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. 37213
    Prev
    Next
    INDEX
    Explanations

    comparison between quantities

    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
    åıĺäºĨ
    -0.10
    éĿ
    -0.10
    åħĥå®Ŀ
    -0.10
    åį§
    -0.09
    ä¸Ģ缴åĪ°
    -0.09
    _EXTRA
    -0.09
    ä¸Ģ缴éĥ½æĺ¯
    -0.09
     sided
    -0.09
    æ±´
    -0.08
    rah
    -0.08
    POSITIVE LOGITS
    è¿ĺä¸įå¦Ĥ
    0.14
    ä½ķåĨµ
    0.13
    缸æ¯Ķä¹ĭä¸ĭ
    0.11
    è¡®
    0.10
    æĽ´ä½ķåĨµ
    0.10
    æ¯Ķ
    0.10
    ä¸İæѤ
    0.10
    è¿ĻçĤ¹
    0.10
     comparable
    0.10
    èĬ¬
    0.10
    Activations Density 0.073%

    No Known Activations