© 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. 36517
    Prev
    Next
    INDEX
    Explanations

    dates and titles

    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
    ç¬ijäºĨ
    -0.09
    /&
    -0.09
    æĬ¥æ¡Ī
    -0.08
    åħ·ä½ĵåĨħ容
    -0.08
    ç¬ij
    -0.08
    ä¸ĭåİ»
    -0.08
    å°»
    -0.08
    -modules
    -0.08
    é«ĺåĩº
    -0.08
    é©´
    -0.07
    POSITIVE LOGITS
    hatt
    0.09
    gis
    0.09
    éĶĮ
    0.09
    onium
    0.09
    isten
    0.09
    충
    0.08
    ieval
    0.08
    -dom
    0.08
    便åı¯
    0.08
    Èļ
    0.08
    Activations Density 0.407%

    No Known Activations