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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 52198
    Prev
    Next
    INDEX
    Explanations

    technical terms and code

    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
     каж
    -0.10
    æľ¬ç«Ļ
    -0.09
    ront
    -0.09
     Bil
    -0.08
    ayah
    -0.08
     bil
    -0.08
     repost
    -0.08
    åŃ£
    -0.07
    Persistence
    -0.07
    .std
    -0.07
    POSITIVE LOGITS
    è¿Ļä¸Ģå¹´
    0.10
    ä»ĸèĩªå·±
    0.10
    æĶ¶çº³
    0.10
    èµł
    0.09
    åįĵ
    0.09
    åĽłä¸ºä»ĸ
    0.09
    æĺ¯ä»ĸ
    0.09
    éĢ
    0.09
    æħ°éĹ®
    0.09
    éħįä»¶
    0.08
    Activations Density 0.062%

    No Known Activations