© 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. 11321
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    çķ¶æĤ¨åľ¨
    -0.24
    使çĶ¨ç¶²è·¯
    -0.22
    æĬĬè¿Ļ个
    -0.22
    mere
    -0.20
    aign
    -0.20
    alli
    -0.20
    uco
    -0.20
    çŀŃ解並
    -0.19
    æľ¬æľįåĭĻ
    -0.19
    جÙĪ
    -0.19
    POSITIVE LOGITS
     clap
    0.19
    å½ĵæŶ
    0.19
     wohl
    0.19
     very
    0.19
     quite
    0.18
     sal
    0.18
     bekan
    0.17
    éĿŀ常åĸľæ¬¢
    0.17
    -for
    0.17
     specific
    0.17
    Activations Density 0.094%

    No Known Activations