© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5042
    Prev
    Next
    INDEX
    Explanations

    special characters in text

    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
    æIJł
    -0.08
    ä¸ĭä¸Ģç¯ĩ
    -0.08
     воÑģ
    -0.08
    ìľ¨
    -0.08
    å¤ļå°ijéĴ±
    -0.07
    onis
    -0.07
    失æķĪ
    -0.07
    æµģåĩº
    -0.07
    çłĶ究æĬ¥åijĬ
    -0.07
    ç®Ģæĺĵ
    -0.07
    POSITIVE LOGITS
    enen
    0.11
    ç¾½æ¯Ľ
    0.09
    .locals
    0.09
    à¸ī
    0.09
     Sounds
    0.09
    ingleton
    0.09
    åįĬ导
    0.09
    ÑģÑĤи
    0.09
    ä¹IJåĽ¢
    0.08
    _CSV
    0.08
    Activations Density 0.007%

    No Known Activations