© 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. 32747
    Prev
    Next
    INDEX
    Explanations

    overall goal

    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
    äºĨä¸Ģåı£
    -0.09
    å²Ķ
    -0.08
    vir
    -0.08
    sha
    -0.08
    æķŀå¼Ģ
    -0.08
    è¯Ŀ
    -0.08
    ä¸Ģå¹ķ
    -0.08
    æ½ŀ
    -0.08
    çĥĻ
    -0.08
    è¦ģåģļåĪ°
    -0.08
    POSITIVE LOGITS
    ç»ıèIJ¥
    0.10
    éĢ£çºĮ
    0.10
    ampo
    0.09
    iban
    0.09
    è¿ŀç»Ń
    0.09
    å°ıå¾®
    0.09
    è´Ł
    0.09
     заÑĢегиÑģÑĤ
    0.09
    éĿ©
    0.09
    æ³ķ人
    0.09
    Activations Density 0.175%

    No Known Activations