© 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. 11240
    Prev
    Next
    INDEX
    Explanations

    top seed, bid, pick, seeds

    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
    åı¦ä¸ĢåįĬ
    -0.20
    åIJĥ饱
    -0.20
    ç§ĴéĴŁ
    -0.20
    æ¡ĥèĬ±
    -0.19
    å¤ĸèµĦ
    -0.19
    anguages
    -0.19
    åį´è¢«
    -0.18
    äºĽè®¸
    -0.18
    çļĦç¼ĺæķħ
    -0.18
     Rhodes
    -0.18
    POSITIVE LOGITS
    uzzi
    0.21
    åĨį
    0.19
    uther
    0.19
    OLA
    0.19
     Gio
    0.19
    iola
    0.19
    áĥ¦
    0.18
    릿
    0.18
    fir
    0.18
    PFN
    0.18
    Activations Density 0.002%

    No Known Activations