© 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. 54675
    Prev
    Next
    INDEX
    Explanations

    egg whites or solids

    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
     вÑģÑİ
    -0.08
    åķĥ
    -0.08
    è¤IJèī²
    -0.08
    åĨį说
    -0.08
    midi
    -0.08
    Scalars
    -0.08
    æ¡©
    -0.08
    ä¸ĭå·´
    -0.08
     Wick
    -0.08
    æ¸į
    -0.08
    POSITIVE LOGITS
    é¹Ħ
    0.09
    æĭ£
    0.09
    EGA
    0.09
    .Canvas
    0.09
    arez
    0.09
    egasus
    0.08
     Morr
    0.08
    ibel
    0.08
    itemap
    0.08
    Lazy
    0.08
    Activations Density 0.053%

    No Known Activations