© 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. 36931
    Prev
    Next
    INDEX
    Explanations

    employ or use

    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
    ãģĦãģĨ
    -0.10
    SSF
    -0.09
    带ç»Ļ
    -0.09
    ÑĢÑĥк
    -0.09
    æĺ¶
    -0.09
    glich
    -0.09
    onium
    -0.09
    лиÑĩ
    -0.08
    á»ijng
    -0.08
    ween
    -0.08
    POSITIVE LOGITS
    è¿Ļç§įæĸ¹æ³ķ
    0.14
    ment
    0.13
    ments
    0.13
    MENT
    0.12
    eur
    0.11
    MENTS
    0.11
    è¿Ļç§įæĸ¹å¼ı
    0.10
    ä¼İ
    0.09
     tactics
    0.09
    äºĨä¸Ģ个
    0.09
    Activations Density 0.024%

    No Known Activations