© 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. 13395
    Prev
    Next
    INDEX
    Explanations

    CREATE TABLE

    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
    éļ¾åº¦
    -0.20
    ç®Ń
    -0.19
    _ioctl
    -0.19
    ä¼ij
    -0.19
     ÑģÑĤепени
    -0.18
     nghiá»ĩm
    -0.18
    ายà¸Ļ
    -0.18
     гаÑĢанÑĤи
    -0.18
    .lazy
    -0.17
    æĿŃ
    -0.17
    POSITIVE LOGITS
    ikon
    0.21
    akk
    0.19
    istan
    0.18
    LinkId
    0.18
    æ®Ħ
    0.18
    cid
    0.17
    æģģ
    0.17
    ä¹°åįķ
    0.17
    ismo
    0.17
    æ´¾
    0.17
    Activations Density 0.004%

    No Known Activations