© 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. 55377
    Prev
    Next
    INDEX
    Explanations

    scores points games win record

    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
    agher
    -0.10
    åİĭè¿«
    -0.09
    é£Łæ¬²
    -0.09
     Mahmoud
    -0.09
    ylon
    -0.09
    isas
    -0.09
    ä¸įæĸŃåľ°
    -0.09
    讪
    -0.09
    çļĦéĩį大
    -0.09
    è½
    -0.09
    POSITIVE LOGITS
    亦
    0.10
    è¾ħåĬ©
    0.09
    anch
    0.08
    ä¹Łå¾Ī
    0.08
    åIJĦèĩª
    0.08
    ä¹Łè¦ģ
    0.07
    为åķ¥
    0.07
    äºĮ代
    0.07
    åIJĮ樣
    0.07
    ainter
    0.07
    Activations Density 0.016%

    No Known Activations