© 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. 13603
    Prev
    Next
    INDEX
    Explanations

    each side of

    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
    ä¹ĭéģĵ
    -0.21
    HEST
    -0.19
    ä¸ĢåįĬ
    -0.18
     quán
    -0.18
    åı¦ä¸ĢåįĬ
    -0.18
    _lhs
    -0.17
    èĩªå·±
    -0.17
    isper
    -0.17
    UNC
    -0.17
    -desc
    -0.17
    POSITIVE LOGITS
     elder
    0.21
    noch
    0.20
    nee
    0.19
    aved
    0.19
    åIJįçīĩ
    0.19
    éķ¿èĢģ
    0.18
    ä¸İæŶ
    0.18
    ä¾į
    0.17
    éĥ½éĿŀ常
    0.17
    lover
    0.17
    Activations Density 0.002%

    No Known Activations