© 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. 21813
    Prev
    Next
    INDEX
    Explanations

    average [noun]

    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
    æłĩæĺİ
    -0.09
    ä¸įå®Į
    -0.09
    elman
    -0.09
    rection
    -0.08
    odal
    -0.08
    vious
    -0.08
     entire
    -0.08
    icker
    -0.08
     Presence
    -0.08
    urga
    -0.08
    POSITIVE LOGITS
    -sized
    0.11
    Joe
    0.11
     Joe
    0.11
    æĹ¥å¸¸å·¥ä½ľ
    0.10
    cy
    0.09
    (avg
    0.09
    -priced
    0.09
    éĨī
    0.09
    .avg
    0.09
    æĿµ
    0.09
    Activations Density 0.019%

    No Known Activations