© 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. 30864
    Prev
    Next
    INDEX
    Explanations

    days of the week or weekend

    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´
    -0.11
    bite
    -0.10
    æľ¬ç½ij
    -0.10
     hone
    -0.10
    æīĭä¸Ń
    -0.09
    åĪ°åľº
    -0.09
     lat
    -0.09
    éĶĭ
    -0.09
     Bite
    -0.09
    åĴ¬
    -0.09
    POSITIVE LOGITS
    ä¸Ģåij¨
    0.11
     weekend
    0.10
    æľ¬åij¨
    0.10
    罩
    0.10
    ä¸Ĭåij¨
    0.10
     week
    0.09
    ltr
    0.09
    åij¨ä¸Ģ
    0.09
     rap
    0.09
    _Res
    0.08
    Activations Density 0.159%

    No Known Activations