© 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. 12899
    Prev
    Next
    INDEX
    Explanations

    adjectives describing qualities

    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
    è¿ĻèĪ¬
    -0.18
    /vnd
    -0.18
    è¡ĮæĶ¿åĮº
    -0.18
    å°±æĺ¯è¿Ļæł·
    -0.18
    нÑıÑĤи
    -0.17
    ][/
    -0.17
    解æĶ¾æĢĿæĥ³
    -0.17
    ениÑİ
    -0.17
    .au
    -0.17
    é«ĺæ¸ħ
    -0.16
    POSITIVE LOGITS
    tsky
    0.23
    WithString
    0.19
    æĸ¯åŁº
    0.18
    纪
    0.18
    nox
    0.18
    cks
    0.17
    enza
    0.17
    eted
    0.17
    å·¨
    0.17
     полно
    0.16
    Activations Density 0.131%

    No Known Activations