© 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. 14262
    Prev
    Next
    INDEX
    Explanations

    promise, precedent, named

    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
    棣
    -0.21
    è°ĭ
    -0.19
    妥
    -0.19
    ä¸įæĺİ
    -0.19
    /misc
    -0.18
    è¬Ģ
    -0.18
    _accessor
    -0.17
    ä¸įæĺİçĻ½
    -0.17
     bout
    -0.17
    ä¸įä¿¡
    -0.17
    POSITIVE LOGITS
     promise
    0.23
     Ñģобой
    0.23
    promise
    0.21
    ä¿Ĺè¯Ŀ说
    0.21
    nameof
    0.20
    æī¿è¯º
    0.20
     precedent
    0.19
    nit
    0.19
    åīįè¾Ī
    0.19
    çīĸ
    0.19
    Activations Density 0.008%

    No Known Activations