© 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. 62948
    Prev
    Next
    INDEX
    Explanations

    press releases or section

    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
    phony
    -0.09
    ÑĤÑı
    -0.09
     distress
    -0.09
    ä»·ä½į
    -0.08
    itched
    -0.08
    pdata
    -0.08
    qualities
    -0.08
    ç«Ļèµ·æĿ¥
    -0.08
    ichen
    -0.08
    alach
    -0.08
    POSITIVE LOGITS
    åĿĬ
    0.11
    sed
    0.11
    ively
    0.10
    å¯Ĵ
    0.10
    eln
    0.09
    gang
    0.09
    [to
    0.09
    creen
    0.09
    uring
    0.09
    åijķ
    0.09
    Activations Density 0.010%

    No Known Activations