© 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. 16263
    Prev
    Next
    INDEX
    Explanations

    Calendar, Circle, KVOController

    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
     familiar
    -0.19
    etten
    -0.19
    åĿŀ
    -0.18
    ness
    -0.18
    è¾Ī
    -0.18
    èĩªçIJĨ
    -0.18
    äºĨ
    -0.17
    anja
    -0.17
    代åĬŀ
    -0.17
    cape
    -0.17
    POSITIVE LOGITS
    âĨĻ
    0.18
    ../
    0.17
    æĹłè®ºå¦Ĥä½ķ
    0.17
    çĻ½æĸij
    0.16
    çīĩåŃIJ
    0.16
    蹩
    0.16
    ä¸Ŀä¸Ŀ
    0.16
     Inline
    0.16
    磬
    0.15
    ç¡ķ
    0.15
    Activations Density 0.197%

    No Known Activations