© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14959
    Prev
    Next
    INDEX
    Explanations

    head, hands, eyes, brow signaling disbelief or 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
    ä¼ĹæīĢ
    -0.22
    棱
    -0.20
    palette
    -0.20
    èī²è°ĥ
    -0.19
    ç¨
    -0.19
    使èĢħ
    -0.19
    éĿ¢ç§¯
    -0.18
    åĹĵåŃIJ
    -0.18
    çļĦç¡®æĺ¯
    -0.18
    .adjust
    -0.17
    POSITIVE LOGITS
    sink
    0.21
    æĦŁåı¹
    0.21
    oval
    0.20
    æijĩ头
    0.20
    adem
    0.20
     wonder
    0.20
    é»ĺ
    0.20
    imson
    0.19
     waste
    0.19
    oley
    0.19
    Activations Density 0.005%

    No Known Activations