© 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. 38276
    Prev
    Next
    INDEX
    Explanations

    near future

    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
    çļĦç¨ĭ度
    -0.10
    arily
    -0.10
    èĥĮåIJİçļĦ
    -0.09
    们çļĦ
    -0.09
    iets
    -0.09
    éĿ¢åīį
    -0.09
    ä¸Ģå®ļçļĦ
    -0.08
    ï¸ı
    -0.08
    们
    -0.08
    æĸ°æĹ¶ä»£
    -0.08
    POSITIVE LOGITS
    æľ
    0.10
    çªģåĩ»
    0.09
    axed
    0.08
    à¹īà¸Ńà¸Ļ
    0.08
    ARDS
    0.08
    èĢĮåĩº
    0.08
    èݨ
    0.08
    çŃĸ
    0.08
     useForm
    0.08
    aghan
    0.08
    Activations Density 0.005%

    No Known Activations