© 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. 17891
    Prev
    Next
    INDEX
    Explanations

    Boost.Units or Boost.Geometry

    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
    举æŃ¢
    -0.10
    oad
    -0.09
    blast
    -0.09
    ´
    -0.09
    ities
    -0.09
    ä¸ĸä¸Ĭ
    -0.08
    ores
    -0.08
    åı¤éķĩ
    -0.08
    è·ļ
    -0.08
    鸮
    -0.08
    POSITIVE LOGITS
    aroo
    0.13
    æĪijçľĭ
    0.10
    rok
    0.10
    pery
    0.09
    lander
    0.09
    åĴĮå®ĮåĸĦ
    0.09
    ingly
    0.09
    åľ©
    0.09
    åIJģ
    0.09
    ie
    0.09
    Activations Density 0.020%

    No Known Activations