© 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. 10707
    Prev
    Next
    INDEX
    Explanations

    jar

    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
    à¹Į
    -0.19
    sing
    -0.18
    sar
    -0.17
    ãģ®ãģĮ
    -0.17
    ãģĥ
    -0.17
    arily
    -0.16
    _callable
    -0.16
    nal
    -0.16
    naire
    -0.16
    sse
    -0.16
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.23
    mates
    0.19
    zelf
    0.18
    (es
    0.17
    gon
    0.17
     proverb
    0.17
    ë¥ĺ
    0.17
    lets
    0.17
    ling
    0.16
    bell
    0.16
    Activations Density 0.006%

    No Known Activations