© 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. 13132
    Prev
    Next
    INDEX
    Explanations

    action or change

    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
    ãģĦãĤĭ
    -0.27
    ãģĹãģ¾ãģĨ
    -0.25
    ãģĦãģ¾ãģĻ
    -0.20
    裳
    -0.18
    çĦ¶æĺ¯
    -0.18
    ç»ıéªĮåĴĮ
    -0.18
    lands
    -0.17
    ãģĹãģ¾ãģĦ
    -0.16
    corn
    -0.16
    uto
    -0.16
    POSITIVE LOGITS
    失误
    0.18
    ingen
    0.17
    able
    0.17
    et
    0.16
    aic
    0.16
    illance
    0.16
    ability
    0.16
     sharper
    0.16
    èĩªå¦Ĥ
    0.15
    举æŃ¢
    0.15
    Activations Density 0.018%

    No Known Activations