© 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. 4477
    Prev
    Next
    INDEX
    Explanations

    perceptions and experiences

    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
    éĢ¶
    -0.09
     Weiner
    -0.09
    leta
    -0.08
    è¡Ģ液循çݯ
    -0.08
     coff
    -0.08
    íħį
    -0.08
    龸
    -0.08
    èī²ç´ł
    -0.08
    heimer
    -0.08
    å°ĸ
    -0.08
    POSITIVE LOGITS
    å¿ĥ缮
    0.12
    åıįæĦŁ
    0.12
    æĦŁçŁ¥
    0.11
    âĢ¢↵↵
    0.10
    å¿ĥ缮ä¸Ń
    0.10
    åĨį说
    0.09
     liv
    0.09
    çŁ¥æĻĵ
    0.09
    หาร
    0.08
    é»Ħæĺı
    0.08
    Activations Density 0.436%

    No Known Activations