© 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. 12764
    Prev
    Next
    INDEX
    Explanations

    Hussein, Ches, indicate

    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
    _stdio
    -0.22
    IPHER
    -0.20
    è¿Ļ项
    -0.19
    èIJĭ
    -0.19
    ãģĵãĤĮãģ¾ãģ§
    -0.19
    rlen
    -0.18
    arsi
    -0.18
    åħ¨éĿ¢èIJ½å®ŀ
    -0.18
     rÃłng
    -0.18
     ÑĤепеÑĢÑĮ
    -0.18
    POSITIVE LOGITS
    æŁIJ个
    0.35
    æŁIJç§į
    0.32
    æŁIJ
    0.30
    æŁIJä¸Ģ
    0.28
    æŁIJäºĽ
    0.23
    ä¸Ģç¯ĩ
    0.23
     certain
    0.21
    èµł
    0.21
    æķħ
    0.20
    åį³å°Ĩ
    0.20
    Activations Density 0.301%

    No Known Activations