© 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. 23843
    Prev
    Next
    INDEX
    Explanations

    scrolling to or within elements

    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
    hev
    -0.09
    -hearted
    -0.09
    å®ļäºĨ
    -0.09
    _compat
    -0.09
    جة
    -0.08
    ponse
    -0.08
    ikon
    -0.08
     suprem
    -0.08
    rous
    -0.08
    iking
    -0.08
    POSITIVE LOGITS
    èŤ
    0.10
    виз
    0.09
    lep
    0.09
    çļ¤
    0.09
    å¿ĥåºķ
    0.09
    人é¡ŀ
    0.09
    æĻĹ
    0.09
    说æĺ¯
    0.09
    ç«ĭãģ¦
    0.09
    pane
    0.09
    Activations Density 0.027%

    No Known Activations