© 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. 30512
    Prev
    Next
    INDEX
    Explanations

    agenda and topics discussed

    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
    à¹Ģà¸Ńà¸ĩ
    -0.09
    æIJŃ
    -0.08
    ç¬ijçĿĢ说
    -0.08
    ä¸ĩ家
    -0.08
    è¿Ļæł·è¯´
    -0.08
    èĥľ
    -0.08
    éĨ¯
    -0.08
    æľĢæĹ©çļĦ
    -0.08
    reasonable
    -0.08
    adin
    -0.08
    POSITIVE LOGITS
     topics
    0.17
    è®®é¢ĺ
    0.15
    çļĦè¯Ŀé¢ĺ
    0.15
    è¯Ŀé¢ĺ
    0.14
    topics
    0.14
    讨论
    0.12
    Topics
    0.12
     Topics
    0.12
    çķħ
    0.11
     вопÑĢоÑģÑĭ
    0.11
    Activations Density 0.231%

    No Known Activations