© 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. 27489
    Prev
    Next
    INDEX
    Explanations

    compensation and indemnity

    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
    пÑĥÑģк
    -0.10
    å®ĺæĸ¹å¾®ä¿¡
    -0.10
    æŨ
    -0.09
    nost
    -0.09
    çĥĽ
    -0.08
    _locator
    -0.08
    ç¶ļ
    -0.08
    à¹Ģà¸ģร
    -0.08
    æĢ¥
    -0.08
    絡
    -0.08
    POSITIVE LOGITS
    è¡¥åģ¿
    0.24
    èµĶåģ¿
    0.21
     compensation
    0.18
     compens
    0.18
     compensate
    0.17
     Compensation
    0.16
    弥补
    0.15
     compensated
    0.15
    èµİ
    0.14
    èµĶä»ĺ
    0.10
    Activations Density 0.054%

    No Known Activations