© 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. 27033
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and questions

    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
    äºĮèĢħ
    -0.09
    ï¼
    -0.08
    æĬ½
    -0.07
    SES
    -0.07
     Pearce
    -0.07
     Peb
    -0.07
     Walnut
    -0.07
     conceived
    -0.07
    åįłæį®
    -0.07
    loom
    -0.07
    POSITIVE LOGITS
    ãĥijãĤ¤
    0.10
     irrational
    0.10
    å¡ŀ
    0.10
    rious
    0.09
    æĭ´
    0.09
    稣
    0.09
    çļĦæĸĩåĮĸ
    0.08
    éĿĴéĵľ
    0.08
     deflate
    0.08
    ä¾ij
    0.08
    Activations Density 0.210%

    No Known Activations