© 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. 49279
    Prev
    Next
    INDEX
    Explanations

    eating and meals

    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
     tide
    -0.08
     Commerce
    -0.08
    este
    -0.08
     clums
    -0.08
     ⣨
    -0.08
    æ¯ıä½į
    -0.07
    cha
    -0.07
    legen
    -0.07
    æ¯ı个人éĥ½
    -0.07
    CHA
    -0.07
    POSITIVE LOGITS
    olla
    0.10
    çĶ·ç¥ŀ
    0.09
    禽
    0.09
    åįİå¤ı
    0.09
    åľ¨ä»ĸçļĦ
    0.09
    èī³
    0.09
    åľ¨æĪijçļĦ
    0.09
    èĨ
    0.09
    åľ¨å®¶éĩĮ
    0.09
    åľ¨ä»ĸ
    0.09
    Activations Density 0.009%

    No Known Activations