© 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. 38699
    Prev
    Next
    INDEX
    Explanations

    one but two

    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
    avn
    -0.10
    ERGE
    -0.10
    å§ļæĺİ
    -0.10
    å¾Ĺä½ı
    -0.10
    ึà¸ģ
    -0.10
    æĹģ
    -0.09
    LTR
    -0.09
    é¾Ħ
    -0.09
    æįº
    -0.09
    uos
    -0.09
    POSITIVE LOGITS
     two
    0.11
    èĢĮæĺ¯
    0.10
    两个
    0.10
     multiple
    0.09
    æľīåĩłä¸ª
    0.09
    好åĩłä¸ª
    0.09
    ä¸ī个
    0.09
    两次
    0.08
    åıĮéĩį
    0.08
     mind
    0.08
    Activations Density 0.006%

    No Known Activations