© 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. 14014
    Prev
    Next
    INDEX
    Explanations

    audio/visual data

    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
    ../
    -0.19
    aday
    -0.19
    .appspot
    -0.19
    åĴĮåıijå±ķ
    -0.19
    å§Ĵ
    -0.18
    iders
    -0.18
    帼
    -0.18
    skin
    -0.17
    ä½ľé£İ建设
    -0.17
    abouts
    -0.17
    POSITIVE LOGITS
    /video
    0.21
    èĪ«
    0.19
    çĽĽå®´
    0.19
     capitals
    0.19
    ptic
    0.18
    åķµ
    0.18
    èĬĭ
    0.18
    转载请
    0.18
    writing
    0.18
    typing
    0.18
    Activations Density 0.010%

    No Known Activations