© 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. 15805
    Prev
    Next
    INDEX
    Explanations

    release information

    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
    éľĢè¦ģ注æĦı
    -0.22
    éĢĤ度
    -0.22
    è¯ŃéŁ³
    -0.22
    DOM
    -0.21
    çĸĥ
    -0.20
    çķ¦
    -0.20
    æĸĽ
    -0.20
     Insets
    -0.20
    å£
    -0.20
    åĤ¾
    -0.19
    POSITIVE LOGITS
     поÑģколÑĮ
    0.20
     ÐŁÐ¾Ñĩем
    0.20
     púb
    0.20
     подÑĢобн
    0.19
    hest
    0.19
    íĹĢ
    0.19
    ulg
    0.19
     Púb
    0.19
    eken
    0.19
     заÑĢегиÑģÑĤ
    0.19
    Activations Density 0.016%

    No Known Activations