© 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. 16250
    Prev
    Next
    INDEX
    Explanations

    book and bog

    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
    ouri
    -0.27
    ÎĬ
    -0.21
    .linkedin
    -0.20
    roat
    -0.20
    æĶ¾æĺł
    -0.20
    inges
    -0.20
    .gstatic
    -0.20
    HttpResponse
    -0.20
    annes
    -0.20
    æį¯
    -0.19
    POSITIVE LOGITS
    çİ©æ³ķ
    0.28
    修订
    0.26
    ä¿®æĶ¹
    0.24
    å®Įå¤ĩ
    0.23
    详ç»ĨçļĦ
    0.23
    ç¹ģ
    0.23
    åŁŁ
    0.23
    åıijå¸ĥ
    0.23
    详ç»Ĩ
    0.22
    å¾Īå¤ļçݩ家
    0.22
    Activations Density 0.050%

    No Known Activations