© 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. 29707
    Prev
    Next
    INDEX
    Explanations

    cursor movement or states

    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
     оÑĤкÑĢÑĭва
    -0.11
    ç©¿è¡£
    -0.10
    etto
    -0.10
    åħ³éŨ
    -0.09
    URNS
    -0.09
    æ±Łå±±
    -0.09
    é³į
    -0.09
    åıijæĮ¥ä½ľçĶ¨
    -0.09
    æĭħ
    -0.09
    è¿ľæĻ¯
    -0.09
    POSITIVE LOGITS
     cursor
    0.13
    (cursor
    0.12
    cursor
    0.11
    åĩĨ
    0.11
    æĤ¬
    0.11
    åħī
    0.10
    å¢ĥ
    0.10
    	cursor
    0.10
    åıŁ
    0.09
    .Cursor
    0.09
    Activations Density 0.090%

    No Known Activations