© 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. 31580
    Prev
    Next
    INDEX
    Explanations

    listing food items

    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
    _Content
    -0.10
    Ùħات
    -0.09
     Ñģм
    -0.09
    zk
    -0.09
     bl
    -0.09
    è¿Ļç§įæĥħåĨµ
    -0.09
    ook
    -0.09
    æĹłæĦı
    -0.08
     interp
    -0.08
    æ§
    -0.08
    POSITIVE LOGITS
    éħįå¥Ĺ
    0.11
    饮æĸĻ
    0.10
    ä¾Ľæ°´
    0.09
    è¾ħåĬ©
    0.09
    踢
    0.09
    optional
    0.09
    éħį件
    0.09
    ThreadId
    0.08
     дополниÑĤелÑĮно
    0.08
    é¡»
    0.08
    Activations Density 0.047%

    No Known Activations