© 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. 26606
    Prev
    Next
    INDEX
    Explanations

    personality, traits, factors, behavior

    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
    æĬ±ä½ı
    -0.10
     Mov
    -0.09
    çĸ±
    -0.09
     ëĶ°
    -0.09
    itage
    -0.09
    sat
    -0.09
    笼
    -0.09
    请æķĻ
    -0.09
    mob
    -0.08
    æįĤ
    -0.08
    POSITIVE LOGITS
    æĢ§æł¼
    0.29
    çļĦæĢ§æł¼
    0.26
     personality
    0.23
    个æĢ§
    0.20
     Personality
    0.20
     traits
    0.20
    äººæł¼
    0.20
    çī¹è´¨
    0.19
     personalities
    0.19
    èĦ¾æ°Ķ
    0.18
    Activations Density 0.096%

    No Known Activations