© 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. 16419
    Prev
    Next
    INDEX
    Explanations

    meetups and setuptools import

    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
    祯
    -0.18
    åĽ½å®¶æĪĺçķ¥
    -0.18
    为æĬĵ
    -0.18
    鸢
    -0.17
     ÑĤоваÑĢ
    -0.17
    ided
    -0.17
    telegram
    -0.17
    å¾Ń
    -0.17
    çļĩåŃIJ
    -0.17
    äºĮèĥİ
    -0.17
    POSITIVE LOGITS
     вз
    0.20
    æ³ķ人
    0.20
    ophon
    0.20
    _PD
    0.18
    fund
    0.18
    IMATE
    0.18
    ¬ģ
    0.17
     groups
    0.17
    亲
    0.17
    åħħ满
    0.17
    Activations Density 0.002%

    No Known Activations