© 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. 27286
    Prev
    Next
    INDEX
    Explanations

    technical 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
    1
    -0.09
    icamente
    -0.09
    5
    -0.08
     Vac
    -0.08
    8
    -0.08
    9
    -0.07
    4
    -0.07
    æĹłæ¯Ķ
    -0.07
    weise
    -0.07
    0
    -0.07
    POSITIVE LOGITS
    åIJĮç±»
    0.14
    éĤ£æł·
    0.13
    ä¸Ģæł·
    0.12
    éĤ£ç§į
    0.10
    éĤ£æł·çļĦ
    0.10
    æīĢæıIJä¾ĽçļĦ
    0.10
    æīĢèĥ½
    0.10
    çľĭä»ĸ
    0.10
    ä¹ĭç±»
    0.09
    èĢĮæĺ¯
    0.09
    Activations Density 0.478%

    No Known Activations