© 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. 10903
    Prev
    Next
    INDEX
    Explanations

    pie followed by chart or related

    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
    sing
    -0.20
    edException
    -0.18
    ä¸Ģ个éĹ®é¢ĺ
    -0.17
    parsed
    -0.17
    æŶæĹ¶å½©
    -0.16
    ses
    -0.16
    纪å§Ķ
    -0.15
    xious
    -0.15
    rieg
    -0.15
    æĹħ游å±Ģ
    -0.15
    POSITIVE LOGITS
    æł·çļĦ
    0.17
    kest
    0.17
    /qu
    0.16
    uther
    0.16
    lets
    0.16
    worm
    0.15
    agle
    0.15
    Ø¡
    0.15
     chances
    0.15
    ù
    0.15
    Activations Density 0.010%

    No Known Activations