© 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. 26653
    Prev
    Next
    INDEX
    Explanations

    eating before exercising

    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
    两天
    -0.13
    æ¯ı天éĥ½
    -0.11
    ä¸Ģåij¨
    -0.10
    ä¸Ģå¤ľ
    -0.10
    è¿Ļ两天
    -0.10
    ä¸ī天
    -0.10
    -days
    -0.10
    ä¸Ńç§ĭèĬĤ
    -0.10
    对æѤ
    -0.10
    å¤ľéĩĮ
    -0.10
    POSITIVE LOGITS
     Hands
    0.09
    cott
    0.09
    ania
    0.09
    åĩī
    0.08
    Hands
    0.08
     cooling
    0.08
    ä¸ĥåħ«
    0.08
    æŶéĹ´æ®µ
    0.08
    hm
    0.08
    åĨ·åį´
    0.08
    Activations Density 0.060%

    No Known Activations