© 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. 19206
    Prev
    Next
    INDEX
    Explanations

    chicken and chicken dishes

    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
    cka
    -0.09
    vä
    -0.08
    imuth
    -0.08
     Ban
    -0.08
    ä¸ŃåĽ½çī¹èī²
    -0.08
     Zucker
    -0.08
    ç
    -0.08
    á»įng
    -0.08
    ÃĹ↵↵
    -0.07
    inois
    -0.07
    POSITIVE LOGITS
    鸡
    0.12
    èĭ´
    0.11
    ени
    0.10
    é¸Ń
    0.09
     chickens
    0.09
    ä¸įä¸ĭ
    0.09
    鹤
    0.09
    ãģ²ãģ¨
    0.09
     poultry
    0.09
     chicken
    0.09
    Activations Density 0.021%

    No Known Activations