© 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. 54132
    Prev
    Next
    INDEX
    Explanations

    solution, cure, or fix

    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
    å·ī
    -0.10
    诮
    -0.09
    guarded
    -0.09
    ç¾
    -0.09
     ÐĴаÑģ
    -0.09
    iatric
    -0.08
    念
    -0.08
    oya
    -0.08
    memcmp
    -0.08
    主æĮģåı¬å¼Ģ
    -0.08
    POSITIVE LOGITS
    解åĨ³æĸ¹æ¡Ī
    0.28
     solution
    0.27
    解åĨ³
    0.24
    solution
    0.23
     solutions
    0.23
    解決
    0.22
     ÑĢеÑĪение
    0.20
     íķ´ê²°
    0.19
     Solution
    0.19
    Solution
    0.19
    Activations Density 0.180%

    No Known Activations