© 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. 53329
    Prev
    Next
    INDEX
    Explanations

    media player

    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
    ç»Ń
    -0.10
    èģĶ社
    -0.10
    çºĮ
    -0.10
    elman
    -0.09
    éľīç´ł
    -0.09
    Americ
    -0.09
    累累
    -0.08
    è·¯ä¸Ĭ
    -0.08
    æŀļ
    -0.08
    FTER
    -0.08
    POSITIVE LOGITS
    ÑĤоп
    0.09
    对äºİæĪij们
    0.09
    _hal
    0.08
     доб
    0.08
     Sark
    0.08
    ר×Ĵ
    0.08
    å¤ıæĹ¥
    0.08
    æľ¯
    0.08
    hire
    0.08
    /wait
    0.08
    Activations Density 0.021%

    No Known Activations