© 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. 37153
    Prev
    Next
    INDEX
    Explanations

    past decades

    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
    çªĹå¤ĸ
    -0.10
    ä¿¡å¿ĥ
    -0.09
    æ°¨éħ¸
    -0.09
    дÑĥм
    -0.09
    è¿Ļæīįæĺ¯
    -0.09
    èĥĽ
    -0.09
    åĪ°æŶåĢĻ
    -0.09
    æĪIJåijĺåįķä½į
    -0.09
    anela
    -0.09
    egasus
    -0.09
    POSITIVE LOGITS
    们
    0.11
    们éĥ½
    0.09
    åĢij
    0.09
    roe
    0.09
    -era
    0.08
    son
    0.08
    ÑģÑĭ
    0.08
    s
    0.08
    们çļĦ
    0.08
    ward
    0.08
    Activations Density 0.032%

    No Known Activations