© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9112
    Prev
    Next
    INDEX
    Explanations

    uptime and availability

    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
    го
    -0.11
    å¤ļåIJį
    -0.10
    ARB
    -0.10
    å½±éŁ³
    -0.10
    åIJİ代
    -0.09
    迤
    -0.09
    毡
    -0.09
     Barry
    -0.09
    bsolute
    -0.09
    ä¸Ģæī¹
    -0.09
    POSITIVE LOGITS
     uptime
    0.13
    åħ¨å¹´
    0.12
    è¿ŀç»Ń
    0.11
    æīĵåį¡
    0.10
     habit
    0.09
    éķ¿å¯¿
    0.09
    éĢ£çºĮ
    0.09
    ä¸įéĹ´æĸŃ
    0.09
     attendance
    0.09
    åĩºå¸Ń
    0.09
    Activations Density 0.084%

    No Known Activations