© 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. 13671
    Prev
    Next
    INDEX
    Explanations

    forum discussion

    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
     lã
    -0.20
    åħ¶æīĢ
    -0.19
    ä¹ĭæīĢ
    -0.18
    éİ
    -0.18
    .business
    -0.17
     Demp
    -0.17
    鼷æĸ¯
    -0.17
    wij
    -0.17
     precaution
    -0.17
    )>>
    -0.17
    POSITIVE LOGITS
    æĿ¥äºĨ
    0.21
    æĸĩåĮĸ建设
    0.20
    èģĴ
    0.19
     sẵn
    0.19
     Atmos
    0.19
    å¦į
    0.19
    éķ¿å¤§äºĨ
    0.18
     participates
    0.18
    主ä½ĵ
    0.18
    _AREA
    0.18
    Activations Density 0.004%

    No Known Activations