© 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. 31015
    Prev
    Next
    INDEX
    Explanations

    books and media

    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
    ä¸ĵå±ŀ
    -0.10
    ä¸ĵ享
    -0.09
    çĶļèĩ³è¿ŀ
    -0.09
    æķĻæ¡Ī
    -0.09
    åİŁåĪĽ
    -0.09
    ocode
    -0.09
    çģµæĦŁ
    -0.09
    ä¸įå°ıçļĦ
    -0.09
    ä¸įå°ı
    -0.08
    é£İæݧ
    -0.08
    POSITIVE LOGITS
    åĽ«
    0.09
    æĪij认为
    0.09
    ansson
    0.09
    æļ¾
    0.08
    æĪijåĸľæ¬¢
    0.08
    ãĤĴè¦ĭãģ¦
    0.08
     Grip
    0.08
    äºĨä¸Ģéģį
    0.08
    æĪijä¼ļ
    0.08
    æݨèįIJ
    0.08
    Activations Density 0.165%

    No Known Activations