© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10451
    Prev
    Next
    INDEX
    Explanations

    eating habits and healthy diet

    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
    è·ª
    -0.09
    åĨĽäºĭ
    -0.09
    åIJĪä¸Ģ
    -0.08
    udy
    -0.08
    åĬłåĢį
    -0.08
    èģĶåĬ¨
    -0.08
    ttp
    -0.08
    åħ¥æīĭ
    -0.08
    til
    -0.08
    å¾Ĵ
    -0.08
    POSITIVE LOGITS
    olls
    0.10
    åĿĩè¡¡
    0.10
    è¡
    0.10
    crypt
    0.10
    éĢĤéĩı
    0.09
     ÐľÐ°Ðº
    0.09
    éĴ±åĮħ
    0.09
    éĢĤå½ĵ
    0.09
    身ä½ĵåģ¥åº·
    0.09
     пÑĢизна
    0.09
    Activations Density 0.032%

    No Known Activations