© 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. 31185
    Prev
    Next
    INDEX
    Explanations

    first item/occurrence

    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
    åı¦ä¸Ģæĸ¹éĿ¢
    -0.09
    еле
    -0.09
    çıĪ
    -0.09
    çĩ®
    -0.09
    æ¬ł
    -0.08
     cref
    -0.08
    ×Ĺת
    -0.08
    èĤĮ
    -0.08
    ÑĪе
    -0.08
    æģĤ
    -0.08
    POSITIVE LOGITS
    æĹ©æĹ©
    0.11
    å°ĸ
    0.10
    å¾ĢåIJİ
    0.09
    caling
    0.09
    OfFile
    0.09
    /top
    0.09
    wend
    0.08
    çĭŃ
    0.08
    çĭIJçĭ¸
    0.08
    Æij
    0.08
    Activations Density 0.176%

    No Known Activations