© 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. 5846
    Prev
    Next
    INDEX
    Explanations

    categories of nouns

    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
    zos
    -0.09
    æĺ¯ä¸Ģç§į
    -0.09
    æ¹
    -0.09
     Javier
    -0.09
    hil
    -0.08
    ä¹Łæĺ¯ä¸Ģç§į
    -0.08
    çļĦä¸ĢéĿ¢
    -0.08
    æĥĬ人
    -0.08
    ZONE
    -0.08
    è¿Ļ个æĹ¶ä»£
    -0.08
    POSITIVE LOGITS
    åĴĮåľ°åĮº
    0.14
    åIJĦæľī
    0.11
    -specific
    0.11
    pecific
    0.11
    诸å¦Ĥ
    0.10
    åIJĦèĩªçļĦ
    0.10
     whose
    0.10
    åħ·ä½ĵçļĦ
    0.10
    çļĦåħ·ä½ĵ
    0.09
    ä¹ĭéĹ´çļĦ
    0.09
    Activations Density 0.547%

    No Known Activations