© 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. 36566
    Prev
    Next
    INDEX
    Explanations

    bit resolution, integer, data, word, digital

    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
    æŁ´
    -0.10
    å·´å·´
    -0.09
    å¸ĸåŃIJ
    -0.08
     деле
    -0.08
    ç·£
    -0.08
    æ®Ĭ
    -0.08
     Provid
    -0.08
    ç¼ĺ
    -0.08
    竹
    -0.08
    evin
    -0.07
    POSITIVE LOGITS
    çİĭåĽ½
    0.11
    cep
    0.10
    æĢİä¹Īçľĭ
    0.10
    ãģİ
    0.10
    tent
    0.09
     Alma
    0.09
    OTES
    0.09
    ä¸ĢåıĮ
    0.09
    вели
    0.09
     blinking
    0.09
    Activations Density 0.112%

    No Known Activations