© 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. 37555
    Prev
    Next
    INDEX
    Explanations

    artificial intelligence and psychology

    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
    èĪ«
    -0.09
    å°ıå§IJå§IJ
    -0.09
    æĬ½å¥ĸ
    -0.08
    å°¾
    -0.08
    ç³Ł
    -0.08
    åĨįæĿ¥
    -0.08
    èĪį
    -0.08
    Void
    -0.08
    ç»´æĿĥ
    -0.08
    çļĦè¡£æľį
    -0.08
    POSITIVE LOGITS
    人工æĻºèĥ½
    0.11
    æĻºèĥ½
    0.10
    æľºåĻ¨
    0.10
    æ²¾
    0.10
     Intelligence
    0.09
    .impl
    0.09
     intelligence
    0.09
     Ø¢ÙĦ
    0.09
    AI
    0.09
     AI
    0.09
    Activations Density 0.043%

    No Known Activations