© 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. 16555
    Prev
    Next
    INDEX
    Explanations

    socks

    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
    è¿«
    -0.21
    åĴĢ
    -0.20
    é£İåIJ¹
    -0.18
    è¿«ä¸įåıĬ
    -0.18
    quist
    -0.18
    åĪ»
    -0.18
    åľŃ
    -0.17
    childs
    -0.17
    inar
    -0.17
     fran
    -0.17
    POSITIVE LOGITS
    è¢ľ
    0.28
     socks
    0.27
    sWith
    0.22
    纩
    0.21
    /to
    0.20
    帼
    0.19
    ðŁı»
    0.19
    ware
    0.19
    ðŁ§
    0.19
     toes
    0.18
    Activations Density 0.003%

    No Known Activations