© 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. 11657
    Prev
    Next
    INDEX
    Explanations

    mail sender and recipient

    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
    误
    -0.08
    ä¼ĺåħĪ
    -0.08
    anja
    -0.08
     Slash
    -0.08
    åĬ³
    -0.08
    å°Ĭ
    -0.08
    åĵªæĢķ
    -0.07
    åºķ线
    -0.07
    èĢĹ
    -0.07
    纹
    -0.07
    POSITIVE LOGITS
    å·¥ä½ľæľºåĪ¶
    0.10
    æ¡Ĩæŀ¶
    0.09
    æĿ¥åĽŀ
    0.09
     bezpo
    0.09
    hooks
    0.09
    framework
    0.09
    éĴ©
    0.09
    ä¸ĢæĬĬ
    0.09
    æľºåĪ¶
    0.09
    管çIJĨåĴĮ
    0.09
    Activations Density 1.669%

    No Known Activations