© 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. 20352
    Prev
    Next
    INDEX
    Explanations

    domains and vocabulary

    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
    æ£Ģ
    -0.09
    è§Ħç«łåĪ¶åº¦
    -0.08
    寡
    -0.08
    ãģ²ãģ¨
    -0.08
    æµģåĬ¨
    -0.08
    éĵ¨
    -0.08
    æ®ģ
    -0.08
    æķĿ
    -0.08
    å«Į
    -0.08
    ilee
    -0.08
    POSITIVE LOGITS
    é¢ĨåŁŁ
    0.14
    domain
    0.13
    é¢ĨåŁŁçļĦ
    0.13
     domain
    0.12
    (domain
    0.11
    éłĺåŁŁ
    0.11
    -domain
    0.11
    _domain
    0.10
    åŁŁ
    0.10
    è¿Ļ个è¡Įä¸ļ
    0.10
    Activations Density 0.115%

    No Known Activations