© 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. 12075
    Prev
    Next
    INDEX
    Explanations

    Cir

    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
    æµģåĬ¨
    -0.20
    æµģåħ¥
    -0.19
    sdk
    -0.19
    åĮĸè¿Ľç¨ĭ
    -0.18
    pag
    -0.18
    Untitled
    -0.18
    ãģ¡ãģ¯
    -0.18
    åģľçķĻ
    -0.18
    ṫ
    -0.17
    æĺŁåħī
    -0.17
    POSITIVE LOGITS
    ä¸Ģæĸ¹éĿ¢
    0.20
    ly
    0.19
    èĪ«
    0.19
    EFF
    0.19
    满
    0.19
    éĹ³
    0.18
    aye
    0.18
    大åݦ
    0.18
    饰
    0.17
    REP
    0.17
    Activations Density 0.002%

    No Known Activations