© 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. 19835
    Prev
    Next
    INDEX
    Explanations

    names such as Wang, Bowen

    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
    iqu
    -0.10
    oÄŁ
    -0.09
    ë§ģ
    -0.09
    å¤¸å¼ł
    -0.08
    igner
    -0.08
    ppe
    -0.08
    .opensource
    -0.08
    scal
    -0.08
    UGHT
    -0.08
    åĪ»
    -0.08
    POSITIVE LOGITS
    itude
    0.10
    emplo
    0.09
    æįį
    0.09
    é¹Ĩ
    0.09
    æ±
    0.09
    ä¹ŁéĿŀ常
    0.08
    ä¸įä¹ı
    0.08
    ÑĥÑĢ
    0.08
     Bowen
    0.08
    _float
    0.08
    Activations Density 0.415%

    No Known Activations