© 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. 14770
    Prev
    Next
    INDEX
    Explanations

    soap opera, SOAP class, soap/

    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
    igon
    -0.20
    åķģ
    -0.18
    鸩
    -0.17
     Alger
    -0.17
    æ¡İ
    -0.17
    æĢ¨
    -0.17
    åĢ¾
    -0.17
    .equ
    -0.16
    avor
    -0.16
    _Component
    -0.16
    POSITIVE LOGITS
    åĪ¶åĵģ
    0.21
    maker
    0.20
    åĪ¶æĪIJ
    0.19
    ean
    0.19
    åĿĬ
    0.19
     Cutter
    0.19
    ðŁı»
    0.19
    ylon
    0.19
    åİĤ
    0.18
    stone
    0.18
    Activations Density 0.003%

    No Known Activations