© 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. 18669
    Prev
    Next
    INDEX
    Explanations

    the purpose of this study

    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
    ould
    -0.10
    Trail
    -0.10
    å¯Į
    -0.09
    \.
    -0.09
    ACE
    -0.09
    好çľĭçļĦ
    -0.08
    çļĦ羣å®ŀæĢ§
    -0.08
    egl
    -0.08
    èģĺ
    -0.08
    ãģĨãģ¡ãģ«
    -0.08
    POSITIVE LOGITS
    ä¼į
    0.09
    管çIJĨåĴĮ
    0.08
    Persist
    0.08
    æIJĢ
    0.08
    éļıå¤Ħ
    0.08
    æľ¬æ¬¡
    0.08
    ãģ¾ãģ¨
    0.08
    æŃª
    0.08
    å°¢
    0.08
    æķ´çIJĨ
    0.07
    Activations Density 1.337%

    No Known Activations