© 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. 48646
    Prev
    Next
    INDEX
    Explanations

    days, dates, and time periods

    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
    åįĬå¹´
    -0.14
    _year
    -0.12
     year
    -0.11
    å¹´åĨħ
    -0.11
    	TokenName
    -0.11
    å¹´åºķ
    -0.10
    æĺİå¹´
    -0.10
    ä¸Ģå¹´
    -0.10
     год
    -0.10
    ä¸ĬåįĬå¹´
    -0.10
    POSITIVE LOGITS
    iram
    0.08
    æ¯ıæĹ¥
    0.08
    åĩºåħ¥
    0.08
    kul
    0.08
    çħ¤
    0.08
     quot
    0.08
    ereo
    0.07
    éĹªçĶµ
    0.07
    neas
    0.07
    hausen
    0.07
    Activations Density 0.184%

    No Known Activations