© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37259
    Prev
    Next
    INDEX
    Explanations

    point of view

    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
    olest
    -0.09
    æĹº
    -0.09
    æĻ®
    -0.09
    裹
    -0.09
    lando
    -0.08
    lef
    -0.08
    makers
    -0.08
    èĹķ
    -0.08
    æĢ§å¼º
    -0.08
    ç«¿
    -0.08
    POSITIVE LOGITS
    çļĦè§Ĵ度
    0.20
    è§Ĵ度æĿ¥çľĭ
    0.20
     perspective
    0.20
    è§Ĵ度çľĭ
    0.19
    æĸ¹éĿ¢
    0.19
    è§Ĩè§Ĵ
    0.17
     standpoint
    0.17
    è§Ĵ度
    0.17
     perspectives
    0.17
    åĩºåıij
    0.16
    Activations Density 0.048%

    No Known Activations