© 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. 34462
    Prev
    Next
    INDEX
    Explanations

    historical names and words

    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
     sham
    -0.09
    uder
    -0.09
     Chancellor
    -0.09
    éľ¹
    -0.08
     unc
    -0.08
    å·¥åķĨ
    -0.08
    å¨ĥå¨ĥ
    -0.08
    æľ¨è´¨
    -0.08
    wed
    -0.08
    翼
    -0.08
    POSITIVE LOGITS
    æŶéļĶ
    0.15
    ç»ıåħ¸çļĦ
    0.12
    ä¼łç»Ł
    0.12
    çĻ¾å¹´
    0.11
    åı²
    0.10
     classics
    0.10
    ä¾ĿçĦ¶
    0.10
    histor
    0.10
     traditional
    0.10
    åIJİ代
    0.10
    Activations Density 0.402%

    No Known Activations