© 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. 11707
    Prev
    Next
    INDEX
    Explanations

    send an email

    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
    arend
    -0.17
    ÅĽ
    -0.17
    cmc
    -0.17
    êt
    -0.16
    aud
    -0.16
    sut
    -0.16
    imat
    -0.16
    lic
    -0.15
    rent
    -0.15
    дов
    -0.15
    POSITIVE LOGITS
    äºĨ大éĩıçļĦ
    0.21
    OrUpdate
    0.21
    ings
    0.20
    ب
    0.19
    äºĨä¸Ģ份
    0.19
    liness
    0.17
    ç»Ļèĩªå·±
    0.17
    ners
    0.17
    idos
    0.17
    ä¸Ģ举
    0.17
    Activations Density 0.030%

    No Known Activations