© 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. 3136
    Prev
    Next
    INDEX
    Explanations

    you agree

    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
    è¥ŀ
    -0.10
    åĬŀäºĭ
    -0.10
    æĭİ
    -0.10
    认æ¸ħ
    -0.10
    éĿ¢åŃIJ
    -0.09
    妥åĸĦ
    -0.09
    åĤĻ
    -0.09
     пÑĢоведениÑı
    -0.09
    è¿IJæ°Ķ
    -0.09
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.09
    POSITIVE LOGITS
     fri
    0.09
    daq
    0.08
    urple
    0.08
    raquo
    0.08
    èİ·å¾ĹæĽ´å¤ļ
    0.08
    ijľ
    0.08
    è¿Ľåħ¥
    0.08
     da
    0.08
     inverted
    0.08
    竹
    0.08
    Activations Density 0.003%

    No Known Activations