© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20505
    Prev
    Next
    INDEX
    Explanations

    HP electronic

    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
    æĶ
    -0.10
    åIJĦ个æĸ¹éĿ¢
    -0.10
    è¿ĺä¸įå¦Ĥ
    -0.09
    à¸ļà¸Ĺ
    -0.08
    è¯ħ
    -0.08
    Ĥæķ°
    -0.08
    /rc
    -0.08
    oreach
    -0.08
    人为
    -0.08
     kick
    -0.08
    POSITIVE LOGITS
    åĽºå®ļçļĦ
    0.10
    åħ·æľīä¸Ģå®ļ
    0.10
    è§Ħå®ļçļĦ
    0.10
    主æµģ
    0.10
    缴æİ¥
    0.10
    å®ĺæĸ¹
    0.09
    æŃ£å¸¸çļĦ
    0.09
    èĩªå·±
    0.09
     official
    0.09
    .serialization
    0.09
    Activations Density 0.378%

    No Known Activations