© 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. 38204
    Prev
    Next
    INDEX
    Explanations

    cost savings

    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
    ains
    -0.10
     Kı
    -0.09
    å¾Ĵ
    -0.09
    atee
    -0.09
    çIJ¬
    -0.09
    樾
    -0.09
    æķ£åıij
    -0.09
    ани
    -0.09
    ãģ¾ãģĦ
    -0.09
    åºŁ
    -0.09
    POSITIVE LOGITS
    åĴĮåıijå±ķ
    0.09
    äºĽ
    0.08
    ä½ĵçİ°åľ¨
    0.08
     Grove
    0.08
     coun
    0.08
    ä¸İåıijå±ķ
    0.08
    è¿İ
    0.08
    ereg
    0.08
    é¢ĩ
    0.08
    侥幸
    0.08
    Activations Density 0.011%

    No Known Activations