© 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. 3352
    Prev
    Next
    INDEX
    Explanations

    Windows related terms and technologies

    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
    çļĦ人çĶŁ
    -0.09
    èģ¿
    -0.09
    åİ¿æĶ¿åºľ
    -0.08
    é¦Ĩ
    -0.08
    Scr
    -0.08
    untime
    -0.08
    路段
    -0.07
    ick
    -0.07
    èĬ±çº¹
    -0.07
     Robertson
    -0.07
    POSITIVE LOGITS
    çĻ¾ç§ij
    0.10
    ä¸Ĭæľī
    0.09
    äºĶè¡Į
    0.09
    è¾¹ä¸Ĭ
    0.09
    irut
    0.09
    æ³ķè§Ħ
    0.09
    ä¸Ĭåİ»
    0.09
    è°ĭ
    0.09
    ÂŃs
    0.09
    pedia
    0.09
    Activations Density 0.121%

    No Known Activations