© 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. 1953
    Prev
    Next
    INDEX
    Explanations

    food and dining experiences

    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
    羸
    -0.09
    å¼ĢèįĴ
    -0.09
    ä¼ģä¸ļåıijå±ķ
    -0.09
    æĥķ
    -0.09
     tar
    -0.08
    reff
    -0.08
    _nat
    -0.08
    Tar
    -0.08
    (Api
    -0.08
    ÑĤаÑĢ
    -0.08
    POSITIVE LOGITS
    ç¾İé£Ł
    0.17
    ç¾İåij³
    0.15
    é£Łçī©
    0.14
    é£Łåĵģ
    0.14
    å°ıåIJĥ
    0.13
     food
    0.12
     foods
    0.11
    à¸Ńร
    0.11
    food
    0.11
    ç¾İåij³ãģĹãģĦ
    0.11
    Activations Density 0.065%

    No Known Activations