© 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. 14358
    Prev
    Next
    INDEX
    Explanations

    by way of clarification

    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
     célib
    -0.20
    (pack
    -0.19
    å¹³åĿĩæ¯ı
    -0.19
    çĦ¡è«ĸ
    -0.19
    æŃ£å¦Ĥ
    -0.19
    çĻĶ
    -0.19
    å½ĵä¹ĭ
    -0.19
     originals
    -0.18
    åħ³éĶ®æĺ¯
    -0.18
    ãģ¾ãģ¾
    -0.18
    POSITIVE LOGITS
    è¿Ļç§įæĸ¹å¼ı
    0.33
    å®ŀéĻħè¡ĮåĬ¨
    0.22
    mez
    0.20
    å®ĥåı¯ä»¥
    0.20
    æĸ¹å¼ı
    0.20
    å¤ļç§įå½¢å¼ı
    0.20
     method
    0.20
    way
    0.19
    è¿Ļç§įæĸ¹æ³ķ
    0.19
    ä¸Ģç³»åĪĹ
    0.19
    Activations Density 0.082%

    No Known Activations