© 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. 57712
    Prev
    Next
    INDEX
    Explanations

    at times

    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
     Vox
    -0.10
    /reg
    -0.09
    çĻ»åľº
    -0.09
    大å¤ļ
    -0.09
    tam
    -0.09
    å·®ä¸įå¤ļ
    -0.09
     hatch
    -0.09
    ç§Ń
    -0.09
    ä¸Ńæľī
    -0.09
    ever
    -0.09
    POSITIVE LOGITS
     flor
    0.10
    æķ´ä¸ª
    0.09
    æĪij羣çļĦ
    0.09
    人士
    0.09
     outs
    0.09
    æĪijæĬĬ
    0.09
    /if
    0.09
    ansas
    0.09
    ìĪĻ
    0.09
     rfl
    0.09
    Activations Density 0.007%

    No Known Activations