© 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. 13023
    Prev
    Next
    INDEX
    Explanations

    #!/usr/bin/env programming languages

    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
    èĥ¥
    -0.19
    è§ĩ
    -0.19
    istics
    -0.18
     nonzero
    -0.18
    /tool
    -0.18
    íĿ¬
    -0.18
    heed
    -0.18
    åĪĿæģĭ
    -0.17
     //=
    -0.17
    误åĮº
    -0.17
    POSITIVE LOGITS
    ä¸ºçĽ®çļĦ
    0.19
    bill
    0.18
     JP
    0.17
     bill
    0.17
     Kinder
    0.17
    åģļçļĦ
    0.17
    æķ¢
    0.17
    åģļå·¥
    0.17
    .US
    0.17
    navbarSupportedContent
    0.17
    Activations Density 1.603%

    No Known Activations