© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 961
    Prev
    Next
    INDEX
    Explanations

    personality types and traits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    æĭĺçķĻ
    -0.26
    è®°å½ķ
    -0.26
    éĢĥèĦ±
    -0.25
    _losses
    -0.25
    æ¶Īæ¯Ĵ
    -0.24
    /posts
    -0.24
     gettimeofday
    -0.23
     tighten
    -0.23
     rooftop
    -0.23
     vandalism
    -0.23
    POSITIVE LOGITS
    æĢ§æł¼
    0.50
     traits
    0.43
    çļĦæĢ§æł¼
    0.42
     personality
    0.40
    个æĢ§
    0.38
     Traits
    0.38
     Personality
    0.37
    åģı好
    0.36
     temperament
    0.35
     preferences
    0.34
    Activations Density 0.046%

    No Known Activations