© 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. 32880
    Prev
    Next
    INDEX
    Explanations

    body stretching and exercises

    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
    å¦ĩ女
    -0.10
     bid
    -0.09
    å·´æĭī
    -0.08
    éĺ¶æ¢¯
    -0.08
    æķ²
    -0.08
    å±Ĥå±Ĥ
    -0.08
    çĶ¨æĪ·åIJį
    -0.08
    æī¿
    -0.08
    çıĬ
    -0.08
    糸
    -0.08
    POSITIVE LOGITS
    åģĩ
    0.10
    ç¿Ģ
    0.09
    梦è§ģ
    0.09
    ADER
    0.09
    èĥ½åĬĽå¼º
    0.09
    çľł
    0.09
    çľĭä¸įæĩĤ
    0.09
    outines
    0.09
    lig
    0.09
    éĻ©
    0.09
    Activations Density 0.076%

    No Known Activations