© 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. 3469
    Prev
    Next
    INDEX
    Explanations

    regular attendance and participation

    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
    çĮ·
    -0.11
     Continent
    -0.09
    äº²çľ¼
    -0.09
     pics
    -0.09
    åĶ¤éĨĴ
    -0.09
    åŀĽ
    -0.09
    ä¸ĸ人
    -0.09
    èµĤ
    -0.09
    éĻIJæŶ
    -0.08
    è¿IJæ²³
    -0.08
    POSITIVE LOGITS
    Regular
    0.13
    éł»
    0.13
     Regular
    0.13
    é¢ij
    0.13
     frequ
    0.13
     regular
    0.13
    regular
    0.12
    å®ļæľŁ
    0.12
     regularly
    0.12
    é¢ijç¹ģ
    0.11
    Activations Density 0.076%

    No Known Activations