© 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. 53326
    Prev
    Next
    INDEX
    Explanations

    prediction of following words

    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
    ä»İå°ı
    -0.09
    otta
    -0.09
    æħ
    -0.09
    èĥª
    -0.09
    çĴŁ
    -0.09
    ç´¯
    -0.09
    ä¹Ĺ
    -0.09
    grown
    -0.08
    æĴĩ
    -0.08
    çŀĴ
    -0.08
    POSITIVE LOGITS
    æµģåĩº
    0.12
    è°´
    0.09
    çĤĬ
    0.09
    é£İæ°Ķ
    0.09
    ä¸įè¦ģ太
    0.09
    æľĢä½İ
    0.09
    è·³èĪŀ
    0.09
    æĮģä¹ħ
    0.08
    åľºæīĢ
    0.08
    大çģ«
    0.08
    Activations Density 0.006%

    No Known Activations