© 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. 26369
    Prev
    Next
    INDEX
    Explanations

    expiration date

    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
    饴
    -0.09
    onga
    -0.09
    éĺī
    -0.09
    /math
    -0.09
     ÑĤек
    -0.09
    hea
    -0.09
    åĬ¨èį¡
    -0.08
     Ñĩа
    -0.08
    åħ¬å¼Ģ课
    -0.08
    ä¾£
    -0.08
    POSITIVE LOGITS
    ãĤĴè¿İ
    0.11
    igu
    0.09
    çĦ¶æĺ¯
    0.09
    èĻij
    0.09
    带走
    0.09
    addon
    0.09
    Jay
    0.09
    setLayout
    0.08
    igion
    0.08
    ently
    0.08
    Activations Density 0.030%

    No Known Activations