© 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. 13894
    Prev
    Next
    INDEX
    Explanations

    first best most valuable

    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
    etto
    -0.24
    çĶ¨åĵģ
    -0.20
     anmeld
    -0.20
    èħ¹
    -0.19
    etti
    -0.19
    æľīè¿Ļæł·çļĦ
    -0.19
    åIJį
    -0.18
    æ¯į
    -0.18
    rement
    -0.18
     conf
    -0.17
    POSITIVE LOGITS
    umper
    0.20
    nger
    0.20
    æĴ¸
    0.20
    heit
    0.19
    tra
    0.19
    ener
    0.18
    æĮģå¹³
    0.18
    анÑĤ
    0.18
    åĪ©åĻ¨
    0.18
    çĺ¢
    0.18
    Activations Density 0.002%

    No Known Activations