© 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. 20782
    Prev
    Next
    INDEX
    Explanations

    period or time duration

    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
    cher
    -0.11
    å¹³æŶ
    -0.10
    éĩįçĤ¹é¢ĨåŁŁ
    -0.09
     Bris
    -0.09
    pur
    -0.08
     CW
    -0.08
    å³Ń
    -0.08
    ä¸Ģæĸ¹
    -0.08
    mind
    -0.08
     Rs
    -0.07
    POSITIVE LOGITS
    åij¼åĶ¤
    0.10
    å¿«æĬ¥
    0.10
    OOD
    0.09
    леÑĩ
    0.09
    INTR
    0.09
    çľ¼æ³ª
    0.09
    emachine
    0.09
    èĥĮéĥ¨
    0.09
    elder
    0.09
    åĬ£åĬ¿
    0.09
    Activations Density 0.026%

    No Known Activations