© 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. 14776
    Prev
    Next
    INDEX
    Explanations

    location in County

    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
    ç®Ĺæĺ¯
    -0.20
    anton
    -0.20
    ANTS
    -0.19
     Burgess
    -0.19
    èŁ²
    -0.18
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.18
    è¡·
    -0.18
    éĴİ
    -0.18
    çŃīä¸Ģæī¹
    -0.18
    æĬ¹
    -0.18
    POSITIVE LOGITS
     ÑģооÑĤвеÑĤ
    0.23
     obviously
    0.23
     itself
    0.22
    å®ŀéĻħ
    0.21
    æľ¬èº«å°±æĺ¯
    0.20
    ãģ¯ãĤĤãģ¡ãĤįãĤĵ
    0.20
    nit
    0.20
    æľ¬èº«
    0.20
    çļĦä¸ĢåĪĩ
    0.20
    æľ¬èº«çļĦ
    0.19
    Activations Density 0.916%

    No Known Activations