© 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. 1069
    Prev
    Next
    INDEX
    Explanations

    compensation, bonuses, performance, reward

    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
    段
    -0.10
    pta
    -0.09
    åºķçĽĺ
    -0.09
    è¿Ĥ
    -0.09
     Monster
    -0.09
     пÑĢоиÑģ
    -0.08
    æľī许å¤ļ
    -0.08
    .Resume
    -0.08
    åİŁåŀĭ
    -0.08
    ä¸ĵå±ŀ
    -0.08
    POSITIVE LOGITS
    å¥ĸåĬ±
    0.17
    èĸªéħ¬
    0.16
    æ¿ĢåĬ±
    0.15
    åijĺå·¥
    0.15
    å¥ĸéĩij
    0.13
    åĵ¡å·¥
    0.12
     employee
    0.11
    å¹´èĸª
    0.11
    ä»İä¸ļ
    0.11
     Reward
    0.10
    Activations Density 0.081%

    No Known Activations