© 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. 16321
    Prev
    Next
    INDEX
    Explanations

    atmosphere, natural phenomena, Nobel award

    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
    ÑģÑĥд
    -0.19
    ives
    -0.19
    .choices
    -0.18
     cục
    -0.18
    anax
    -0.18
    AFX
    -0.18
    Ñīик
    -0.18
     Undo
    -0.18
    omatic
    -0.18
     inline
    -0.17
    POSITIVE LOGITS
    ä¸įå¼Ģ
    0.22
    -like
    0.21
    æł·
    0.21
    è°¢
    0.21
    åľ°éĿ¢
    0.20
    çİ°æľī
    0.20
    æ¨¡æł·
    0.19
     earthly
    0.19
    çİ°æľīçļĦ
    0.19
     strengths
    0.18
    Activations Density 0.138%

    No Known Activations