© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52457
    Prev
    Next
    INDEX
    Explanations

    names ending in a, ina, ette, tine, and similar

    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
    peare
    -0.12
    quip
    -0.09
    -Sah
    -0.09
     newcom
    -0.09
     VOID
    -0.09
    otch
    -0.08
    обоÑĢ
    -0.08
    ucher
    -0.08
    gett
    -0.08
    åįĥä¸ĩä¸įè¦ģ
    -0.08
    POSITIVE LOGITS
    ERN
    0.09
    ern
    0.09
    .sf
    0.08
    å«ģç»Ļ
    0.08
    ä¸įçIJĨ
    0.08
    姣
    0.08
    entina
    0.08
    ies
    0.08
    eso
    0.08
    æĸ©
    0.08
    Activations Density 0.067%

    No Known Activations