© 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. 12056
    Prev
    Next
    INDEX
    Explanations

    complete feedback, document delivery, play recording

    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
    .tip
    -0.22
    hei
    -0.19
    .flash
    -0.19
    zes
    -0.19
     flash
    -0.19
    PropertyParams
    -0.19
    andin
    -0.18
    /site
    -0.18
    IBUT
    -0.18
     ëĬ
    -0.18
    POSITIVE LOGITS
    æĪĸèĢħæĺ¯
    0.26
    OrCreate
    0.24
    æĪĸæĺ¯
    0.24
    æĪĸèĢħåħ¶ä»ĸ
    0.23
    便ä¼ļ
    0.23
    éĥ½æĥ³
    0.22
    è¿Ľåħ¥
    0.21
    åį§å®¤
    0.21
    ä¸Ģ个æĸ°çļĦ
    0.21
    éĢī项
    0.20
    Activations Density 0.104%

    No Known Activations