© 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. 26704
    Prev
    Next
    INDEX
    Explanations

    numbers and delimiters

    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
    对人ä½ĵ
    -0.10
    èįı
    -0.09
    带走
    -0.09
    ä¸Ģçľĭ
    -0.09
    对æīĭ
    -0.09
    ä¸ŀ
    -0.09
     Presenter
    -0.09
    rael
    -0.09
    好åIJĹ
    -0.08
    zu
    -0.08
    POSITIVE LOGITS
    é¹Ħ
    0.10
    髯
    0.09
    ãģªãģĦãģĵãģ¨
    0.08
    大åݦ
    0.08
    æĹ¶ä»£ä¸ŃåĽ½
    0.08
    åı·çº¿
    0.08
    chron
    0.08
    ä½ķå¿ħ
    0.08
    åĥħ
    0.08
    IDD
    0.07
    Activations Density 0.275%

    No Known Activations