© 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. 16645
    Prev
    Next
    INDEX
    Explanations

    characters starting with Po, F, or M

    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
    æĺĻ
    -0.24
    ä»Ĭ天çļĦ
    -0.23
    è¸Ĭ
    -0.20
    éª
    -0.20
    ugo
    -0.19
     меÑĤалл
    -0.19
     ÐIJлекÑģан
    -0.19
    çĶ©
    -0.18
     Eagle
    -0.18
    ç°ª
    -0.18
    POSITIVE LOGITS
    æĮļ
    0.20
    marsh
    0.20
    好åıĭ
    0.19
    chwitz
    0.19
    èħ¹
    0.18
    èĦ¾
    0.18
     Saud
    0.18
    mur
    0.18
    este
    0.18
    ousel
    0.18
    Activations Density 0.001%

    No Known Activations