© 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. 31117
    Prev
    Next
    INDEX
    Explanations

    field of invention

    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
    çĿ¨
    -0.10
    æĭįæĭį
    -0.09
     squirt
    -0.09
    owie
    -0.09
    æĸĻ
    -0.09
    rovers
    -0.09
    annie
    -0.09
    ÑĢин
    -0.09
     sprink
    -0.09
    nis
    -0.09
    POSITIVE LOGITS
    èķĥ
    0.10
    çªĴæģ¯
    0.09
    æįĨ
    0.09
    çĵľ
    0.09
    æİī
    0.09
     pole
    0.08
    ë°©ìĨ¡
    0.08
    æ¦ķ
    0.08
    ç©·
    0.08
    åħĪéĶĭ
    0.08
    Activations Density 0.028%

    No Known Activations