© 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. 12051
    Prev
    Next
    INDEX
    Explanations

    salivary glands

    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
    linger
    -0.10
    ä¸įè§ģ
    -0.09
    modifiable
    -0.09
    æł¸å¿ĥæĬĢæľ¯
    -0.09
    èµĢ
    -0.09
    èļĢ
    -0.09
    è·µ
    -0.08
    çļĦæĶ¿æ²»
    -0.08
    IZER
    -0.08
    éĽı
    -0.08
    POSITIVE LOGITS
    æľĽ
    0.09
    è¶ĬæĿ¥è¶Ĭå°ij
    0.09
     saliva
    0.09
    æīĵåĵį
    0.09
    è´ª
    0.09
    åŀĤ
    0.09
    erland
    0.09
    åįŀ
    0.09
    -mails
    0.09
    å¢ŀè¿Ľ
    0.09
    Activations Density 0.069%

    No Known Activations