© 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. 2962
    Prev
    Next
    INDEX
    Explanations

    not yet configured or selected

    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
    æĥij
    -0.10
    UIS
    -0.10
    è¿ĺæĺ¯è¦ģ
    -0.09
    vox
    -0.09
    èĤĵ
    -0.09
    éĽĨä¸Ńåľ¨
    -0.09
    é¢IJ
    -0.09
    /help
    -0.09
    å¿Į
    -0.09
    айл
    -0.09
    POSITIVE LOGITS
    夯
    0.08
    istribute
    0.08
    çĽĸ
    0.08
    pte
    0.08
     Anast
    0.07
     unm
    0.07
     mutil
    0.07
    thumbs
    0.07
     Crosby
    0.07
    人
    0.07
    Activations Density 0.013%

    No Known Activations