© 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. 16402
    Prev
    Next
    INDEX
    Explanations

    state of mind or knowledge

    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
    ovation
    -0.20
    ENN
    -0.18
    _INCLUDED
    -0.18
     ÑĤÑĭÑģÑı
    -0.18
    为æ°ij
    -0.18
    Ñģка
    -0.18
    梳
    -0.17
     inquiries
    -0.17
    ÃŃf
    -0.17
    cpy
    -0.17
    POSITIVE LOGITS
    æľ¬èĥ½
    0.20
    åĵĦ
    0.20
    æĮ½
    0.20
     <=>
    0.19
    /il
    0.18
    è°´
    0.18
    æľ¬ç½ijç«Ļ
    0.18
    usted
    0.18
    ned
    0.18
     ÐĴедÑĮ
    0.18
    Activations Density 0.005%

    No Known Activations