© 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. 22450
    Prev
    Next
    INDEX
    Explanations

    working with groups or individuals

    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
     dep
    -0.10
    emark
    -0.09
     Sisters
    -0.09
    é©»
    -0.09
     DAM
    -0.08
    åįıåIJĮ
    -0.08
    oop
    -0.08
    åIJĮä¼´
    -0.08
    /random
    -0.08
     prof
    -0.08
    POSITIVE LOGITS
    æīĵ交éģĵ
    0.14
    clients
    0.11
    ÑĤан
    0.10
    åĩ«
    0.09
    تÙĤ
    0.09
    绳
    0.09
    客æĪ·çļĦ
    0.08
    å¯Įè´µ
    0.08
    åĴĻ
    0.08
    管çIJĨå·¥ä½ľ
    0.08
    Activations Density 0.082%

    No Known Activations