© 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. 54025
    Prev
    Next
    INDEX
    Explanations

    roles and conditions

    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
     Acrobat
    -0.09
    ×¢×Ŀ
    -0.08
    Ø´ÙĬ
    -0.08
    ⣶
    -0.08
    鸣
    -0.08
    ifica
    -0.08
     liking
    -0.07
    软
    -0.07
     sockaddr
    -0.07
    éĻ
    -0.07
    POSITIVE LOGITS
    åľ°å¸¦
    0.11
    èĪ¬çļĦ
    0.10
    åIJĦå¼ı
    0.09
    ulous
    0.09
    å¸ļ
    0.09
    bones
    0.09
    å°±åľ¨äºİ
    0.09
    0.09
    Pocket
    0.09
    heads
    0.08
    Activations Density 0.298%

    No Known Activations