© 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. 57427
    Prev
    Next
    INDEX
    Explanations

    flexible time and pace

    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
    plain
    -0.11
    强è¡Į
    -0.10
    åIJİ代
    -0.10
    ocard
    -0.10
    æĻļä¼ļ
    -0.09
    å°Ŀ
    -0.09
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    -0.09
    rop
    -0.09
    ocre
    -0.08
    PLAIN
    -0.08
    POSITIVE LOGITS
    çģµæ´»æĢ§
    0.12
    Flex
    0.11
     flexibility
    0.11
    çģµæ´»
    0.11
     Flex
    0.11
    flex
    0.11
     flex
    0.10
    èĩªåľ¨
    0.10
    Flexible
    0.10
     flexible
    0.10
    Activations Density 0.067%

    No Known Activations