© 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. 61652
    Prev
    Next
    INDEX
    Explanations

    scientific nomenclature

    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
    íĻĢ
    -0.09
    ä¸įçŁ¥
    -0.09
    tre
    -0.08
    æľīç§į
    -0.08
    ksz
    -0.08
    ä¸ŃåİŁ
    -0.08
    æ¸ħæĻ¨
    -0.08
    ÑģкиÑħ
    -0.08
    å°¸
    -0.08
    çŃ
    -0.08
    POSITIVE LOGITS
    綦
    0.11
    è¿ĺæĺ¯ä¼ļ
    0.10
    è¿Ļä¹Ī说
    0.09
    èĮµ
    0.09
    ALIGN
    0.09
    åĩłå®¶
    0.09
    è¾Ī
    0.09
    设æĸ½å»ºè®¾
    0.09
    马åħĭæĢĿ
    0.09
    åįģä½³
    0.09
    Activations Density 0.307%

    No Known Activations