© 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. 39103
    Prev
    Next
    INDEX
    Explanations

    to verb

    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
    èIJĿåįľ
    -0.09
    oir
    -0.09
    æł¹åºķ
    -0.09
    æ·»
    -0.09
    åĽŃ
    -0.09
    AGO
    -0.09
    pard
    -0.08
    ä½ĵçİ°åľ¨
    -0.08
    æıIJä¾ĽçļĦ
    -0.08
    æĪĺçķ¥
    -0.08
    POSITIVE LOGITS
    纡
    0.11
    è¿Ļ件äºĭ
    0.10
    æѤäºĭ
    0.09
    è¿Ļä¸Ģ天
    0.09
    æŁIJ个
    0.09
    ä»İäºĭ
    0.09
    åĮºåŁŁæĢ§
    0.09
    èĬĤ
    0.09
    ä¸įåIJĮç¨ĭ度
    0.09
    annie
    0.08
    Activations Density 0.187%

    No Known Activations