© 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. 23732
    Prev
    Next
    INDEX
    Explanations

    course or courses

    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
    åįıä¼ļä¼ļåijĺ
    -0.10
    èľ»
    -0.10
    ãng
    -0.10
    çĵ£
    -0.09
    èĿĻ
    -0.09
    é¦ĸé¢Ĩ
    -0.09
    _CANNOT
    -0.09
    èĽ¹
    -0.09
    离
    -0.08
    æ»ŀ
    -0.08
    POSITIVE LOGITS
    кÑĥÑĢ
    0.11
    人éĢī
    0.11
    /course
    0.09
    åĴĮåľ°åĮº
    0.09
     material
    0.08
     courses
    0.08
    大åĬĽåıijå±ķ
    0.08
    aris
    0.08
    åĬ²
    0.08
    æĸĻçIJĨ
    0.08
    Activations Density 0.041%

    No Known Activations