© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12609
    Prev
    Next
    INDEX
    Explanations

    names ending in 'an' or 'in'

    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
    å±ij
    -0.20
    Scaled
    -0.19
     Geile
    -0.19
    éĽ¹
    -0.18
    unar
    -0.18
    çĸ¤
    -0.18
    æĻļéĹ´
    -0.18
    è¿ľæ´ĭ
    -0.18
    æĢ¨
    -0.18
    宵
    -0.17
    POSITIVE LOGITS
    马æĿ¥
    0.21
    ä¸ĢçŃīå¥ĸ
    0.20
    ä¼łç»Ł
    0.20
    èĢģ人家
    0.20
     telegram
    0.20
    äºĮçŃīå¥ĸ
    0.19
     Aws
    0.19
     Wong
    0.18
    falls
    0.18
    Junior
    0.18
    Activations Density 0.214%

    No Known Activations