© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37490
    Prev
    Next
    INDEX
    Explanations

    conditions and examples

    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
    utar
    -0.09
    顺便
    -0.08
    å¹¿æ³Ľ
    -0.08
    cola
    -0.08
    å¼ĢåĪĽ
    -0.08
    磶
    -0.08
    mant
    -0.08
     reck
    -0.08
    å±ħçĦ¶
    -0.08
    åħħå®ŀ
    -0.08
    POSITIVE LOGITS
    è¿Ļç§įæĥħåĨµ
    0.28
    è¿ĻæŶ
    0.28
    è¿ĻæŶåĢĻ
    0.24
    è¿Ļ个æŶåĢĻ
    0.23
    æѤæŶ
    0.21
    åľ¨è¿Ļç§į
    0.21
    æѤæĻĤ
    0.18
    æĥħåĨµä¸ĭ
    0.16
    æĥħåĨµ
    0.16
    çļĦæĥħåĨµ
    0.15
    Activations Density 0.185%

    No Known Activations