© 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. 13599
    Prev
    Next
    INDEX
    Explanations

    nicknames in quotes

    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
    çļĩåŃIJ
    -0.19
    èĵ¦
    -0.19
    æķ´æķ´
    -0.18
     ÐIJлекÑģан
    -0.18
    даÑĤÑĮ
    -0.18
    è¿Ļ两年
    -0.18
    ARRIER
    -0.17
    oric
    -0.17
    :///
    -0.17
    /null
    -0.17
    POSITIVE LOGITS
     заÑĤ
    0.18
    åĿ¦
    0.17
    swing
    0.17
    ᶣ
    0.17
    èĤĮèĤī
    0.17
    ılm
    0.17
    ç©į
    0.17
    çĶ¨æĪ·æıIJä¾Ľ
    0.17
    çķ¦
    0.17
    æ³¥
    0.17
    Activations Density 0.010%

    No Known Activations