© 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. 33077
    Prev
    Next
    INDEX
    Explanations

    food ingredients, plants, and libraries

    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
    inee
    -0.09
    TD
    -0.09
    åĩ¿
    -0.09
     обла
    -0.08
    steen
    -0.08
    红éħĴ
    -0.08
    å®ŀæŶ
    -0.08
    Pet
    -0.08
     TD
    -0.08
    izzle
    -0.08
    POSITIVE LOGITS
    æ¸ĹéĢı
    0.11
    åĪ¶ä½ľ
    0.09
     dye
    0.09
    ç²½åŃIJ
    0.09
     luaL
    0.09
    åĽ½å®¶å®īåħ¨
    0.09
    rij
    0.09
    onic
    0.09
    ä¹łä¿Ĺ
    0.09
    éģĹæ¼ı
    0.09
    Activations Density 0.042%

    No Known Activations