© 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. 10592
    Prev
    Next
    INDEX
    Explanations

    unknown, missing, determined

    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
    æĬ¬èµ·
    -0.10
    为主çļĦ
    -0.08
    ird
    -0.08
    åı£æ°Ķ
    -0.08
    ä½IJ
    -0.08
    สà¸ĩ
    -0.07
    åѤ
    -0.07
     bi
    -0.07
    ÃĶ
    -0.07
     allot
    -0.07
    POSITIVE LOGITS
    åĩºæĿ¥äºĨ
    0.12
    说åĩºæĿ¥
    0.11
    究竣æĺ¯
    0.11
    æıŃæĻĵ
    0.10
    æij§
    0.10
    害ç¾ŀ
    0.10
    LAY
    0.10
    äºĨåĩºæĿ¥
    0.10
    å¤§éĽ¨
    0.10
    以便
    0.10
    Activations Density 0.327%

    No Known Activations