© 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. 933
    Prev
    Next
    INDEX
    Explanations

    several ways or means

    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
    çIJħ
    -0.08
    ä¸Ģå¥Ĺ
    -0.08
    æĬĺ
    -0.08
    æľįåĬ¡å¹³åı°
    -0.08
    ä¸Ģäºĭ
    -0.08
    äºĨå¤ļå°ij
    -0.07
    ære
    -0.07
    æĺ¯å¤ļä¹Ī
    -0.07
     Marcos
    -0.07
    çłĶ究æĪIJæŀľ
    -0.07
    POSITIVE LOGITS
    红æĺŁ
    0.10
    ä½Ĩä¸įéĻIJ
    0.10
    inja
    0.10
    被认为
    0.09
    ç©Ĩ
    0.09
    uggested
    0.09
    eneral
    0.08
    клÑİÑĩи
    0.08
    aris
    0.08
     fran
    0.08
    Activations Density 0.098%

    No Known Activations