© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52582
    Prev
    Next
    INDEX
    Explanations

    time consuming or saving

    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
    寮
    -0.09
    erea
    -0.09
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.09
    çĹ¿
    -0.09
    uru
    -0.09
    æĬ¥ä»·
    -0.09
    ä¸Ńå¿ĥåŁİåĮº
    -0.09
    æĦ§
    -0.09
     manners
    -0.09
    iban
    -0.08
    POSITIVE LOGITS
    æŶéĹ´åĴĮ
    0.17
    æŶéĹ´
    0.16
    çļĦæŶéĹ´
    0.15
     time
    0.15
    =time
    0.14
    ç²¾åĬĽ
    0.13
     вÑĢемени
    0.13
    æĻĤéĸĵ
    0.13
     ìĭľê°Ħ
    0.12
    time
    0.12
    Activations Density 0.066%

    No Known Activations