© 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. 14071
    Prev
    Next
    INDEX
    Explanations

    copyright notices for Facebook

    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
    楫
    -0.19
    [
    -0.18
     cdr
    -0.18
    èĭĭ
    -0.18
    ç²¾å¿ĥ
    -0.18
    standing
    -0.17
    è¾ij
    -0.17
     planetary
    -0.17
    çŃĸ
    -0.17
     ide
    -0.17
    POSITIVE LOGITS
    åĿ³
    0.23
    bra
    0.23
    rax
    0.20
    顯示
    0.20
    xes
    0.20
    æݥ轨
    0.19
    æĺ¾ç¤º
    0.19
    æĺ¾ç¤ºåĩº
    0.19
    第ä¸Ģ家
    0.19
    æĬĵ好
    0.18
    Activations Density 0.003%

    No Known Activations