© 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. 5985
    Prev
    Next
    INDEX
    Explanations

    xhtml declarations

    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
    çĭ±
    -0.10
    缸
    -0.10
    _locals
    -0.10
    åı¯æĢķ
    -0.10
    etri
    -0.09
    çªĴ
    -0.09
     NOTICE
    -0.09
    .MM
    -0.09
    å¨ĥå¨ĥ
    -0.09
    ÑĥÑĤÑĮ
    -0.09
    POSITIVE LOGITS
    èĪĶ
    0.08
    çĿ¡åīį
    0.08
    iv
    0.08
    /~
    0.08
    urai
    0.07
    æĺ¾
    0.07
    æ¯ı个人çļĦ
    0.07
     pedestrian
    0.07
    æ·Į
    0.07
    uality
    0.07
    Activations Density 0.002%

    No Known Activations