© 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. 57529
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
    æĬķ稿
    -0.09
    æħ°
    -0.09
    éĻ¶
    -0.08
    aza
    -0.08
    åĽĽäºĶ
    -0.08
     виде
    -0.08
    entes
    -0.08
    å®Ľå¦Ĥ
    -0.08
    åįĬå°ıæŶ
    -0.08
    ä¸Ģæīĭ
    -0.08
    POSITIVE LOGITS
    æ¯ıå¹´
    0.09
     ìķŀìľ¼ë¡ľ
    0.09
    /start
    0.08
    è§Ħéģ¿
    0.08
    è°¤
    0.08
     sá»ķ
    0.08
    าà¸Ļ
    0.08
    èĸ¨
    0.08
    Ìģ
    0.08
    ä»ĬåIJİ
    0.08
    Activations Density 0.138%

    No Known Activations