© 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. 33815
    Prev
    Next
    INDEX
    Explanations

    rise or rising

    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¸ĭæĿ¥çļĦ
    -0.11
    æĿĤå¿Ĺ社
    -0.09
    ä¸īåĪĨ
    -0.09
    .emf
    -0.09
    éĴľ
    -0.09
    åĵĨ
    -0.09
    ä¸ĭæĿ¥
    -0.08
     rtl
    -0.08
     Dahl
    -0.08
    à¸Ľà¸²à¸ģ
    -0.08
    POSITIVE LOGITS
    åįĩèµ·
    0.14
    rise
    0.13
     Rising
    0.13
    åįĩ
    0.12
     Rise
    0.12
     rise
    0.12
    rising
    0.12
     rising
    0.12
    æĺĩ
    0.11
    ä¸Ĭåįĩ
    0.10
    Activations Density 0.063%

    No Known Activations