© 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. 11033
    Prev
    Next
    INDEX
    Explanations

    uncertainty or observation

    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
    é¹Ĥ
    -0.11
    æīĵå¼ĢäºĨ
    -0.10
    绫
    -0.09
    èĬ°
    -0.09
    æľīåºı
    -0.09
    èĪĪ趣
    -0.09
    Öģ
    -0.09
    æĪijåĸľæ¬¢
    -0.09
    çŃīå½¢å¼ı
    -0.08
    ä¸įéĶĻ
    -0.08
    POSITIVE LOGITS
    æѤ类
    0.09
    çī¹åĪ«æĺ¯
    0.09
    å°¤åħ¶æĺ¯
    0.09
     apparently
    0.09
    ÑİÑĤ
    0.09
    éĻ¤éĿŀ
    0.08
    çľĭæĿ¥
    0.08
     seemingly
    0.08
    GM
    0.08
    çĽ²çĽ®
    0.08
    Activations Density 0.122%

    No Known Activations