© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7228
    Prev
    Next
    INDEX
    Explanations

    broken, hope, and returns

    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
     basically
    -0.10
    ãģ£ãģ¡ãĤĥ
    -0.08
    è·Ł
    -0.08
    丼æŀĹ
    -0.08
     pretty
    -0.08
    åŁºæľ¬ä¸Ĭ
    -0.08
     everybody
    -0.08
    ä»İæĿ¥æ²¡
    -0.07
    ãģłãģ£ãģŁãĤī
    -0.07
     conce
    -0.07
    POSITIVE LOGITS
    èĭ¥æĤ¨
    0.10
    æĪij们å¿ħé¡»
    0.10
    è¿ĻèĪ¬
    0.10
    åŃ©ç«¥
    0.09
    ä¹ĭ人
    0.09
    ä¹ĭå¿ĥ
    0.09
    èĢĮè¿Ļ
    0.08
    æ¯ıæĹ¥
    0.08
    è¿ĻéĩĮæľī
    0.08
    STALL
    0.08
    Activations Density 0.220%

    No Known Activations