© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 24232
    Prev
    Next
    INDEX
    Explanations

    unnoticed, overlooked, unrecognized, unappreciated

    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
    Negative Logits
    anja
    -0.10
    ä¸įæĥľ
    -0.09
    è¯Ħæµĭ
    -0.09
    èĩªæķij
    -0.09
    ä¸įå¿ħ
    -0.08
    åºķ线
    -0.08
    åı¨
    -0.08
    æ¶ĪçģŃ
    -0.08
    å¿ħä¸įåı¯
    -0.08
    è¿·æĥij
    -0.08
    POSITIVE LOGITS
    èĢģå®ŀ
    0.10
    ritis
    0.10
    èªĵè¨Ģ
    0.10
    ç»Ĩå¾®
    0.09
    è§ĴèIJ½
    0.09
     aspects
    0.09
    IQUE
    0.09
    IED
    0.09
    ä½Ĩåį´
    0.09
    太å¤ļçļĦ
    0.08
    Activations Density 0.110%

    No Known Activations