© 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. 62033
    Prev
    Next
    INDEX
    Explanations

    personal growth and development

    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
    èįī
    -0.12
    å½Ģ
    -0.10
    ä¸ĢåıĮ
    -0.09
    èĮ«
    -0.09
    辫
    -0.09
     зани
    -0.08
    è¢
    -0.08
     essentials
    -0.08
     Barr
    -0.08
    篾
    -0.08
    POSITIVE LOGITS
    æĪIJéķ¿
    0.13
     growth
    0.13
     Growth
    0.13
    å¢ŀéķ¿
    0.11
    æĪIJéķ·
    0.11
    growth
    0.11
    antz
    0.10
    æıIJåįĩ
    0.10
    çļĦæĪIJéķ¿
    0.09
    uni
    0.09
    Activations Density 0.045%

    No Known Activations