© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63772
    Prev
    Next
    INDEX
    Explanations

    personality types

    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
    械
    -0.09
     ske
    -0.09
    讫
    -0.09
    à¹ĩà¸Ķ
    -0.09
    Bid
    -0.09
    ony
    -0.09
    åīįè¡Į
    -0.08
    ?=.*
    -0.08
    è¿Ń
    -0.08
    .Mesh
    -0.08
    POSITIVE LOGITS
     personality
    0.15
    æĢ§æł¼
    0.14
    çļĦæĢ§æł¼
    0.13
    äººæł¼
    0.13
    个æĢ§
    0.12
     personalities
    0.12
     Personality
    0.12
    çī¹è´¨
    0.11
     Jung
    0.10
    åģı
    0.10
    Activations Density 0.067%

    No Known Activations