© 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. 13225
    Prev
    Next
    INDEX
    Explanations

    .dtd and advertisement

    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
     quán
    -0.23
     Doming
    -0.19
    ptune
    -0.18
    _trampoline
    -0.17
    ali
    -0.17
    é¡¿
    -0.17
    gart
    -0.17
    nze
    -0.17
     gou
    -0.17
     LOCK
    -0.17
    POSITIVE LOGITS
    æīĵæŃ»
    0.20
    exact
    0.20
    éªĭ
    0.19
    设æĸ½å»ºè®¾
    0.18
    迹象
    0.18
    ULATION
    0.18
     Hubbard
    0.17
    ç²ij
    0.17
    ä½İ头
    0.17
    åįİå°Ķè¡Ĺ
    0.17
    Activations Density 0.009%

    No Known Activations