© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11369
    Prev
    Next
    INDEX
    Explanations

    assigning blame or responsibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    ä»ĸ们ä¼ļ
    -0.21
    ÑĭÑĪ
    -0.20
    车ä½į
    -0.19
    æľ¬éĴ±
    -0.19
    äºĴåĬ©
    -0.19
    è¿Ļ两ç§į
    -0.19
    çļĦåIJĦç§į
    -0.19
    rait
    -0.19
     viewing
    -0.18
    onet
    -0.18
    POSITIVE LOGITS
     responsible
    0.21
     alone
    0.21
    导èĩ´
    0.19
     chù
    0.19
     revel
    0.19
    å§ĭ
    0.19
    urv
    0.19
    CCR
    0.18
    è´Łè´£
    0.18
    åѤ
    0.18
    Activations Density 0.035%

    No Known Activations