© 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. 57387
    Prev
    Next
    INDEX
    Explanations

    the [noun]

    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
    æĢ»ç»ıçIJĨ
    -0.10
    çļĦæĦŁåıĹ
    -0.09
    ä¹ĭå¤Ħ
    -0.09
    /of
    -0.09
    åĪĻæĺ¯
    -0.09
    odka
    -0.09
    ernel
    -0.08
     налиÑĩие
    -0.08
    ippi
    -0.08
    меÑģ
    -0.08
    POSITIVE LOGITS
    å°±å¤ŁäºĨ
    0.10
    æĪij们ä¸Ģèµ·
    0.09
    羣æĥħ
    0.09
    è§Ĩ线
    0.09
    积æ·Ģ
    0.09
    å·§å¦Ļ
    0.09
    éļľ
    0.09
     ÑģобÑģÑĤвенно
    0.09
    äºĮèĢħ
    0.09
    uss
    0.09
    Activations Density 0.070%

    No Known Activations