© 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. 15881
    Prev
    Next
    INDEX
    Explanations

    Sheriff

    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
    ively
    -0.21
    æĸ°éĹ»åıijå¸ĥ
    -0.19
    rans
    -0.18
    建åħļ
    -0.18
    æĹ¶è¡¨ç¤º
    -0.18
    éĩį大
    -0.17
    endo
    -0.17
    é«ĺåİĭ
    -0.17
    ç®Ģ缴
    -0.17
    aptive
    -0.17
    POSITIVE LOGITS
    ä¸Ģ家
    0.21
    ibu
    0.20
    pedia
    0.19
    blade
    0.18
     indefinite
    0.18
    añ
    0.17
    é£ŀèĪ¹
    0.17
    Ãłng
    0.17
    cko
    0.17
    ÙĨÙĬ
    0.16
    Activations Density 0.001%

    No Known Activations