© 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. 36632
    Prev
    Next
    INDEX
    Explanations

    win or bet

    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
    æĹ¢æľī
    -0.09
    èŀįåIJĪåıijå±ķ
    -0.08
    婵
    -0.08
    p
    -0.07
    çī¢çī¢
    -0.07
    åŃľ
    -0.07
    -side
    -0.07
    éŀ£
    -0.07
    9
    -0.07
    1
    -0.07
    POSITIVE LOGITS
    kontakte
    0.11
    è¿ĻæĿ¡
    0.10
    å¥ĸåĬ±
    0.10
    à¹Ħà¸Ń
    0.10
    çľ¼åīį
    0.10
    é¢Ŀå¤ĸ
    0.09
    åıłåĬł
    0.09
    ANI
    0.09
    转弯
    0.09
    PIO
    0.09
    Activations Density 0.021%

    No Known Activations