© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14970
    Prev
    Next
    INDEX
    Explanations

    MitchellMitchell GoddenMitchell Callahan

    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
    ../../../
    -0.25
    ../../
    -0.20
    iÄĩ
    -0.19
    们
    -0.18
    ãģĦãģĨ
    -0.17
    etime
    -0.17
    æĦıæĢĿ
    -0.17
    .prevent
    -0.16
    asy
    -0.16
    stract
    -0.16
    POSITIVE LOGITS
    ering
    0.18
    hä
    0.16
    aise
    0.16
    à¹Į
    0.16
    ä½ĵåĪ¶æĶ¹éĿ©
    0.15
    ãĥ³ãĤ°
    0.15
     ado
    0.15
    imits
    0.15
    ä¼łåĩº
    0.15
    andest
    0.14
    Activations Density 0.054%

    No Known Activations