© 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. 21995
    Prev
    Next
    INDEX
    Explanations

    than generate

    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
    è¿ĺè®°å¾Ĺ
    -0.09
     Madden
    -0.09
    EGIN
    -0.08
    âģ¾
    -0.08
    éĥĥ
    -0.08
    ihad
    -0.08
    اÙĨا
    -0.08
     atl
    -0.08
    ë¦Ħ
    -0.08
    éĹ´çļĦ
    -0.08
    POSITIVE LOGITS
    ãģ£ãģįãĤĬ
    0.11
    éĺĹ
    0.09
    clud
    0.09
    uth
    0.09
    人人éĥ½
    0.09
    alytics
    0.09
    éĩijåŃĹ
    0.08
    ishes
    0.08
    à¹Ģà¸īà¸ŀาะ
    0.08
    loy
    0.08
    Activations Density 0.020%

    No Known Activations