© 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. 62187
    Prev
    Next
    INDEX
    Explanations

    names and last names

    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
    缪
    -0.09
    ä¹ĹãĤĬ
    -0.09
    å½ķ
    -0.09
    ä¸ĢæŶ
    -0.09
    æ³ķ人
    -0.08
    æķ´ä¸ª
    -0.08
    _CHAN
    -0.08
    OST
    -0.08
     çıkt
    -0.08
    éħ¿
    -0.08
    POSITIVE LOGITS
    å¹²äºĭ
    0.10
    æĴ¬
    0.10
    æķķ
    0.09
    å£ģåŀĴ
    0.09
    ä¸Ģæĸ¹éĿ¢
    0.09
    igos
    0.08
    ovy
    0.08
    elve
    0.08
    æ·¡æ°´
    0.08
     rhet
    0.08
    Activations Density 0.241%

    No Known Activations