© 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. 1068
    Prev
    Next
    INDEX
    Explanations

    numbers, QUESTION, definition

    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
     aforementioned
    -0.11
    è¿ĽæĿ¥
    -0.10
    è¿Ļç±»
    -0.09
    ses
    -0.08
     ÑħоÑĤÑĮ
    -0.08
    ç»Ń约
    -0.08
     ÑħоÑĩÑĥ
    -0.08
    æĭ¢
    -0.08
    åĽŀåįĩ
    -0.07
    峪
    -0.07
    POSITIVE LOGITS
    oret
    0.10
    们
    0.10
    orem
    0.09
    malink
    0.09
    ä¸Ģä¸ĸ
    0.09
    foundland
    0.09
    åijĬ
    0.08
    å°ıçĻ½
    0.08
    èĢģå¦Ī
    0.08
    ä¸Ģ代
    0.08
    Activations Density 0.468%

    No Known Activations