© 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. 63884
    Prev
    Next
    INDEX
    Explanations

    neal / screen / tor+ed

    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
    è¿¢
    -0.09
    èĥ§
    -0.09
    å·³
    -0.09
    éĥijéĩį
    -0.08
    ÑģÑĥ
    -0.08
    便åı¯
    -0.08
    åİ
    -0.08
    åIJijãģį
    -0.08
    ä¹Ĵ
    -0.08
    åĺģ
    -0.08
    POSITIVE LOGITS
    atron
    0.09
    hare
    0.08
    å¹¿æ³ĽçļĦ
    0.08
    éŃĤ
    0.08
    æŃ»äºĨ
    0.08
    çŀ³
    0.08
    ITO
    0.07
    лок
    0.07
    对èĩªå·±
    0.07
    andering
    0.07
    Activations Density 1.328%

    No Known Activations