© 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. 6539
    Prev
    Next
    INDEX
    Explanations

    health and professional guidance

    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
    èĥ¡åŃIJ
    -0.09
     kı
    -0.08
     envelope
    -0.08
    èĬ¬
    -0.08
    ç¾İåĮĸ
    -0.08
    instein
    -0.08
    ÑįÑĤ
    -0.08
    åĿ¦
    -0.08
    tright
    -0.07
    åĤ»
    -0.07
    POSITIVE LOGITS
    çļĦé£Łçī©
    0.12
    é¤IJ
    0.12
    让æ¶Īè´¹èĢħ
    0.10
     Nutrition
    0.10
    é£Łçī©
    0.10
    åģ¥åº·
    0.10
     nutrition
    0.10
    èIJ¥åħ»
    0.10
    åħ¨äº§ä¸ļéĵ¾
    0.10
    èĨ³é£Ł
    0.10
    Activations Density 0.069%

    No Known Activations