© 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. 7708
    Prev
    Next
    INDEX
    Explanations

    RIM Ltd

    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
    骧
    -0.09
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.08
    åĽ½ä¼ļ
    -0.08
    ume
    -0.08
    ç½²
    -0.08
    _Il
    -0.08
    èĨĽ
    -0.08
     ÐŁÑĢе
    -0.08
    äºĮèĢħ
    -0.08
    lingen
    -0.08
    POSITIVE LOGITS
    涣
    0.11
    belt
    0.09
    åĪ³
    0.09
    æļ®
    0.09
    å¯ĴåĨ·
    0.08
    å¯ĤéĿĻ
    0.08
    een
    0.08
    ìĨĶ
    0.08
     Grim
    0.08
    è¿ĺç®Ĺ
    0.08
    Activations Density 0.003%

    No Known Activations