© 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. 23490
    Prev
    Next
    INDEX
    Explanations

    career and academic success

    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
    ç¢ī
    -0.09
    亦
    -0.08
    åIJ¬åIJ¬
    -0.08
    æľīåĪ©äºİ
    -0.08
    aul
    -0.08
    ech
    -0.08
    æ§Ĭ
    -0.08
    çĮ·
    -0.08
    享åıĹåĪ°
    -0.08
    ECH
    -0.08
    POSITIVE LOGITS
    æĪIJè´¥
    0.13
    æķ´ä¸ªäºº
    0.11
    çļĦä¸Ģ项
    0.11
     success
    0.11
    uccess
    0.10
    çļĦä¸Ģ大
    0.10
    èĥ½åIJ¦
    0.10
    ä»»ä½ķä¸Ģ个
    0.10
    çļĦæĪIJåĬŁ
    0.09
    çİij
    0.09
    Activations Density 0.576%

    No Known Activations