© 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. 11255
    Prev
    Next
    INDEX
    Explanations

    factor. induction, expression

    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
    æĪĸèĢħ说
    -0.22
    æĪĸèĢħæĺ¯
    -0.21
    æĪĸèĢħ
    -0.21
    çŁ³æ²¹åĮĸå·¥
    -0.19
     Fors
    -0.18
    å¾ĢåIJİ
    -0.18
    éĢļ常
    -0.18
    Âł
    -0.18
    æľīä¸Ģå®ļçļĦ
    -0.17
    è¿ĺä¸įæĺ¯
    -0.17
    POSITIVE LOGITS
    ipop
    0.21
    ñe
    0.20
    ChangedEventArgs
    0.18
    xBB
    0.18
     ###↵
    0.18
    _vs
    0.18
    kich
    0.18
    onné
    0.18
    AccessException
    0.17
    rü
    0.17
    Activations Density 2.834%

    No Known Activations