© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36287
    Prev
    Next
    INDEX
    Explanations

    with plenty, their, the

    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
    ç»Ļä½łä»¬
    -0.11
    embro
    -0.11
    å¾Īåĸľæ¬¢
    -0.09
    æĸ°å½¢åĬ¿ä¸ĭ
    -0.09
    ä¸Ĭè°ĥ
    -0.09
    usters
    -0.09
    åĬĽè¿ĺæĺ¯
    -0.08
    çľĭäºĨä¸Ģ
    -0.08
    缴å±ŀ
    -0.08
    ло
    -0.08
    POSITIVE LOGITS
    åIJİèĢħ
    0.10
    ogie
    0.09
    สà¸ĸ
    0.09
    quelle
    0.08
    æ¯ı个
    0.08
    çĬ¬
    0.08
    duc
    0.08
    çŃ¹çłģ
    0.08
    ifle
    0.08
    çĶļ
    0.08
    Activations Density 0.102%

    No Known Activations