© 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. 26457
    Prev
    Next
    INDEX
    Explanations

    newsroom center

    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
    éĻ¢éĻ¢éķ¿
    -0.11
    该éĻ¢
    -0.10
    æĦıä¹īä¸Ĭ
    -0.10
    å¹´éĻIJ
    -0.09
    æ®ĵ
    -0.09
    èĨij
    -0.09
    éĻ¢åī¯éĻ¢éķ¿
    -0.09
    çĸĹ
    -0.09
    ä¹ĭ乡
    -0.09
    被éªĹ
    -0.09
    POSITIVE LOGITS
    认
    0.09
    utton
    0.09
    ç¤ģ
    0.08
    æĪIJåijĺ
    0.08
    ï¸
    0.08
    妤
    0.08
    讯
    0.08
    æľī人说
    0.08
     dispatch
    0.08
    olis
    0.08
    Activations Density 0.007%

    No Known Activations