© 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. 13811
    Prev
    Next
    INDEX
    Explanations

    invention and patent language

    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
    ä¸Ģç¬Ķ
    -0.22
    åħ¨ä½ĵ
    -0.20
    åĽº
    -0.20
    IRD
    -0.20
    åıĤåĬłäºĨ
    -0.19
    åIJ¦
    -0.19
    ä¸Ĭå®ĺ
    -0.18
    rnd
    -0.18
    é¢ĨåŁŁ
    -0.18
    Mor
    -0.17
    POSITIVE LOGITS
    èĩ³ä¸Ĭ
    0.21
    omic
    0.20
    ä¸įè¦ģ太
    0.19
    çĤ¹å¤´
    0.19
    -duty
    0.19
    é»ijå¤ľ
    0.19
    èµ·æŃ¥
    0.18
    æIJĤ
    0.18
     Duty
    0.18
    argins
    0.18
    Activations Density 0.019%

    No Known Activations