© 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. 20117
    Prev
    Next
    INDEX
    Explanations

    health and weight

    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
    æĶ¾å¤§
    -0.10
    å°Ĭ严
    -0.09
    æľ¨åľ°æĿ¿
    -0.09
    åħ½
    -0.09
    è´Ŀ
    -0.09
    æħķ
    -0.08
    ystone
    -0.08
    请åıĬæŶ
    -0.08
    éĻ¶çĵ·
    -0.08
     stump
    -0.08
    POSITIVE LOGITS
    åģ¥åº·
    0.16
    åģ¥åº·çļĦ
    0.16
     unhealthy
    0.15
    èĥĸ
    0.14
     health
    0.14
     healthier
    0.13
    èĤ¥èĥĸ
    0.13
     здоÑĢов
    0.12
    身ä½ĵåģ¥åº·
    0.12
    åģ¥
    0.12
    Activations Density 0.412%

    No Known Activations