© 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. 19397
    Prev
    Next
    INDEX
    Explanations

    former or latter pairings

    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
    ä¸İä¼Ĺ
    -0.11
     phá»iji
    -0.11
    è·Łå¥¹
    -0.10
    代è¨Ģ人
    -0.10
    让èĩªå·±
    -0.10
    atron
    -0.10
    åĽłä¸ºå®ĥ
    -0.10
    æ¯ĸ
    -0.09
    éĿ¢åŃIJ
    -0.09
    è·Łä»ĸ
    -0.09
    POSITIVE LOGITS
    åīįèĢħ
    0.18
    åIJİèĢħ
    0.13
     latter
    0.11
    arus
    0.10
    ones
    0.09
    姿
    0.08
    å°¸
    0.08
    iers
    0.08
    æ¡£æ¡Ī
    0.08
    ICES
    0.08
    Activations Density 0.307%

    No Known Activations