© 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. 58283
    Prev
    Next
    INDEX
    Explanations

    company names and titles

    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
    æŦ
    -0.10
    åºľ
    -0.10
    aley
    -0.09
    ãģ¨ãģĦãģĨãĤĤãģ®
    -0.09
    æīĢåľ¨
    -0.09
     обÑīеÑģÑĤвенно
    -0.09
    åī§ä¸Ń
    -0.09
    æ¦Ń
    -0.09
    ç®ĢåİĨ
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    POSITIVE LOGITS
    æĹĹä¸ĭçļĦ
    0.13
     corporation
    0.13
    -sponsored
    0.12
    åĢĴéĹŃ
    0.11
    åħ¬åı¸çļĦ
    0.10
    èij£äºĭéķ¿
    0.10
    åijĺå·¥
    0.10
    æĹĹä¸ĭ
    0.10
    é«ĺ管
    0.09
    -funded
    0.09
    Activations Density 0.288%

    No Known Activations