© 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. 35074
    Prev
    Next
    INDEX
    Explanations

    held up or raises

    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
    alto
    -0.09
    .bootstrap
    -0.09
    é£İ湿
    -0.09
    bench
    -0.09
    æ²ĵ
    -0.09
    prite
    -0.08
     Herbert
    -0.08
    ç¾
    -0.08
    .Disabled
    -0.08
    rap
    -0.08
    POSITIVE LOGITS
    æ±Ĺ
    0.10
    å¼¥
    0.10
    æİ¢
    0.09
    æijĬ
    0.09
    çīĮåŃIJ
    0.09
    éĹ°
    0.09
    éĺİ
    0.08
    à¹Ģà¸īà¸ŀาะ
    0.08
    èŀ³
    0.08
    stances
    0.08
    Activations Density 0.019%

    No Known Activations