© 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. 51461
    Prev
    Next
    INDEX
    Explanations

    click to 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
    ä¹łæĥ¯äºĨ
    -0.10
    à°Ĩ
    -0.09
    绿èī²éĢļéģĵ
    -0.09
    çĤ¹äºĨ
    -0.09
     ÑħоÑĢо
    -0.09
     Gund
    -0.09
    åĸľæ¬¢åIJĥ
    -0.08
    INA
    -0.08
    azor
    -0.08
    è¿Ľåı£
    -0.08
    POSITIVE LOGITS
    æĽ´å¤ļ
    0.10
    éĶĦ
    0.09
    便ä¼ļ
    0.09
    ilen
    0.08
    ÙĨÙĬÙĨ
    0.08
    ize
    0.08
    _DS
    0.08
    italize
    0.08
    æĺ¯ä»¥
    0.08
    berry
    0.08
    Activations Density 0.033%

    No Known Activations