© 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. 27073
    Prev
    Next
    INDEX
    Explanations

    under [something]

    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
    æķ¬ä¸ļ
    -0.09
    éĻIJéĩı
    -0.09
    دÙĤ
    -0.09
    é£İæĻ¯åĮº
    -0.09
    éģµå¾ª
    -0.09
    rics
    -0.09
    解åĨ³éĹ®é¢ĺ
    -0.09
     влад
    -0.09
    å±ĢéĻIJäºİ
    -0.09
    ä¹İ
    -0.09
    POSITIVE LOGITS
    æĪĸå°Ĩ
    0.09
    çļĦå½±åĵį
    0.08
    ä¸ĢèĤ¡
    0.08
    lined
    0.08
    åĮĸçļĦ
    0.08
    YA
    0.08
    æķ£åıijçĿĢ
    0.08
    åĨ¢
    0.08
    ä¸įèµ·
    0.08
    TypeID
    0.07
    Activations Density 0.020%

    No Known Activations