© 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. 38014
    Prev
    Next
    INDEX
    Explanations

    leading position

    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
    åľ¨ç½ijä¸Ĭ
    -0.10
    æIJŃ
    -0.10
    ng
    -0.09
    ê¹IJ
    -0.08
     ваÑĢи
    -0.08
    ucci
    -0.08
    åľ¨æѤ
    -0.08
     speak
    -0.08
    ä¼ĹçŃ¹
    -0.08
    å°ıçĻ½
    -0.08
    POSITIVE LOGITS
    /front
    0.11
    人们对
    0.10
    èħĬ
    0.10
    æĸ°éĹ»è®°èĢħ
    0.10
    åłª
    0.10
    人群ä¸Ń
    0.10
    çŀŃ解
    0.09
    第ä¸Ģæī¹
    0.09
    ç§ijæĬĢè¿ĽæŃ¥
    0.09
    baugh
    0.09
    Activations Density 0.007%

    No Known Activations