© 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. 63172
    Prev
    Next
    INDEX
    Explanations

    eating, weight, obesity, feeding behavior

    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
    æ£ļ
    -0.09
    èĻİ
    -0.09
    éģŃ
    -0.09
    rons
    -0.08
    åĪ¶è£ģ
    -0.08
     Exiting
    -0.08
     Haz
    -0.08
    ç¿ķ
    -0.08
    å¤ĸåĮħ
    -0.08
    èĪħèĪħ
    -0.08
    POSITIVE LOGITS
    ieux
    0.10
    è¿Ľé£Ł
    0.10
    失æݧ
    0.10
    åĽ¤
    0.09
    _ROUND
    0.09
    æĹģ
    0.08
    åIJĥäºĨ
    0.08
    åıĻ
    0.08
    åĤį
    0.08
    æ²»çĹħ
    0.08
    Activations Density 0.129%

    No Known Activations