© 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. 19379
    Prev
    Next
    INDEX
    Explanations

    aesthetic, beauty, looks

    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
    æ²ĵ
    -0.10
    ee
    -0.08
    2
    -0.08
    ossa
    -0.08
    5
    -0.08
    æ¡£
    -0.08
    9
    -0.08
    1
    -0.08
    帽
    -0.08
    æ¾¥
    -0.08
    POSITIVE LOGITS
    ç¾İè§Ĥ
    0.27
    çĪ±ç¾İ
    0.21
    ç¾İåѦ
    0.21
    é¢ľåĢ¼
    0.20
    好çľĭ
    0.20
    审ç¾İ
    0.20
    好çľĭçļĦ
    0.19
     aesthetic
    0.18
     aesthetics
    0.18
    å¤ĸè§Ĥ
    0.17
    Activations Density 0.142%

    No Known Activations