© 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. 15426
    Prev
    Next
    INDEX
    Explanations

    last minute or final moments

    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
    è¿ŀéĶģ
    -0.22
    家åĽŃ
    -0.19
    .setSize
    -0.19
    CM
    -0.19
    åĩºåİ»
    -0.19
    ä¸Ĭå¹´åIJĮæľŁ
    -0.19
    æľīè¿ĩ
    -0.19
    ä¼Ļ
    -0.19
    çĶ·ä¸»
    -0.19
    å¾Īå¿«å°±
    -0.18
    POSITIVE LOGITS
    åĨ²åĪº
    0.23
    ä¹ĭéĻħ
    0.22
    临
    0.21
    (Expected
    0.19
    åĨ³èĥľ
    0.19
    ä¼łæĿ¥
    0.19
    >Last
    0.18
    (bottom
    0.18
    æŶåĪ»
    0.18
    ÙĬØŃ
    0.18
    Activations Density 0.017%

    No Known Activations