© 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. 62699
    Prev
    Next
    INDEX
    Explanations

    possessive 's

    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
    sta
    -0.07
    足
    -0.07
    umas
    -0.07
    ä¸ĸçķĮ第ä¸Ģ
    -0.07
    åľ°åĽ¾
    -0.07
    зи
    -0.07
    storm
    -0.07
    çļĦæĺ¯
    -0.07
    isons
    -0.07
    æ¸ħéĻ¤
    -0.07
    POSITIVE LOGITS
    UPER
    0.11
    ä½°
    0.10
    etical
    0.10
     Kensington
    0.10
    å¤ļãģı
    0.10
    æĭ©
    0.09
    车åŃIJ
    0.09
    é¦ĸä»ĺ
    0.09
    chnitt
    0.09
    atisch
    0.09
    Activations Density 0.088%

    No Known Activations