© 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. 11573
    Prev
    Next
    INDEX
    Explanations

    right field, right-handed, ventricular

    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
    OfWork
    -0.19
    baugh
    -0.19
    ä¼ĺè´¨çļĦ
    -0.19
    æ¾Į
    -0.18
    ARN
    -0.18
    eping
    -0.18
    سÙĦ
    -0.18
    æģ¶å¿ĥ
    -0.17
    idth
    -0.17
    ä¸įéĶĻçļĦ
    -0.17
    POSITIVE LOGITS
    ers
    0.21
    å¨ĺ家
    0.20
    wald
    0.19
    -most
    0.19
    rete
    0.19
    Ãło
    0.19
    åĵ¡
    0.19
     komm
    0.18
    rooms
    0.18
     stint
    0.18
    Activations Density 0.002%

    No Known Activations