© 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. 5345
    Prev
    Next
    INDEX
    Explanations

    Opry member, Kardon, movie, Gimme Chocolate, F-SECURE, Sioux, Asbury Lake

    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
    è£ĺ
    -0.10
    ç¾ŀ
    -0.09
    bu
    -0.08
    çļĭ
    -0.08
    æ½®æµģ
    -0.08
    arus
    -0.08
    anky
    -0.08
    ä¸ĢåIJį
    -0.08
    ioc
    -0.08
    å»Ł
    -0.07
    POSITIVE LOGITS
    zell
    0.12
    thon
    0.10
    _nd
    0.10
    宽æĿ¾
    0.10
    åħ¨å¥Ĺ
    0.09
    åıijå±ķçIJĨ念
    0.09
    ï¸
    0.09
    åĢŁ
    0.09
    纲
    0.09
    平稳
    0.09
    Activations Density 0.002%

    No Known Activations