© 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. 11811
    Prev
    Next
    INDEX
    Explanations

    nationalities followed by roles or affiliations

    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
    绫
    -0.20
    ä¹Ķ
    -0.20
    åĽĽåij¨
    -0.20
    ä¸ĸ人
    -0.20
    Tw
    -0.19
    U
    -0.19
    æĦŁ
    -0.19
    沮丧
    -0.19
    竦
    -0.18
    èĺĸ
    -0.18
    POSITIVE LOGITS
    åľ¨æĪijåĽ½
    0.22
    åľ¨å½ĵåľ°
    0.20
    ç¾±
    0.20
    åĬłæĮģ
    0.19
    çļĦ帮åĬ©ä¸ĭ
    0.19
    çĹķ迹
    0.19
    为主çļĦ
    0.19
    .proc
    0.19
    _hdl
    0.19
    åĶĿ
    0.19
    Activations Density 0.088%

    No Known Activations