© 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. 13325
    Prev
    Next
    INDEX
    Explanations

    WARNING spoiler territory

    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
    æľīåħ´è¶£
    -0.20
    æĿŁ
    -0.19
    arParams
    -0.19
    gom
    -0.19
    åĬŁåĬ³
    -0.19
    ằ
    -0.18
    å¾Īä¸įéĶĻ
    -0.18
    åIJĪéĢĤçļĦ
    -0.18
    åİŁæĿ¥çļĦ
    -0.18
    ä¸įåĬ¨
    -0.18
    POSITIVE LOGITS
    强çĥĪ
    0.21
    åı¯èĥ½å¯¼èĩ´
    0.20
    åı¯èĥ½ä¼ļ
    0.20
    åı¯èĥ½åıijçĶŁ
    0.20
    强çĥĪçļĦ
    0.19
    é¢ĦåijĬ
    0.19
     potentially
    0.18
    åī§çĥĪ
    0.18
    åı¯èĥ½åŃĺåľ¨
    0.18
    çĮĽçĥĪ
    0.18
    Activations Density 0.060%

    No Known Activations