© 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. 31950
    Prev
    Next
    INDEX
    Explanations

    formal reporting verbs

    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
    çŁ¥éģĵèĩªå·±
    -0.09
    æĹłå½¢
    -0.09
    eve
    -0.08
    ä¸ĵ线
    -0.08
    缴éĶĢ
    -0.07
    .Measure
    -0.07
    éħį
    -0.07
    tie
    -0.07
    è¿ľæĸ¹
    -0.07
    èĥĮéĿ¢
    -0.07
    POSITIVE LOGITS
    æıIJ交
    0.16
    æ±ĩæĬ¥
    0.16
    éĢĴ交
    0.14
    åijĪ
    0.14
    ä¸ĬæĬ¥
    0.13
    æĬ¥åijĬ
    0.12
     submit
    0.11
    submitted
    0.11
     submits
    0.11
     submitted
    0.11
    Activations Density 0.038%

    No Known Activations