© 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. 13354
    Prev
    Next
    INDEX
    Explanations

    chromosome loci

    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
    ground
    -0.19
    è¾ĵåįµ
    -0.19
    ãģ¤ãĤĤãĤĬ
    -0.18
    åijĽ
    -0.17
     GAP
    -0.17
    rial
    -0.17
     Derrick
    -0.17
    éļ¾åıĹ
    -0.17
    çºłç»ĵ
    -0.17
    åı£æ°Ķ
    -0.17
    POSITIVE LOGITS
    ä¸Ģå¤Ħ
    0.26
    ä¸ĢåĿĹ
    0.24
    æľ«ç«¯
    0.22
    ä¸Ģ段
    0.21
    ä½ıå®ħ
    0.20
    ä¸Ģ座
    0.20
    ä½įç½®
    0.20
    æĸ°ä¸ī
    0.20
    åĮºåĿĹ
    0.19
    ä¸Ńéĥ¨
    0.19
    Activations Density 0.106%

    No Known Activations