© 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. 13710
    Prev
    Next
    INDEX
    Explanations

    the [noun]

    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
    dì
    -0.20
    çĶ¨æĪ·æıIJä¾Ľ
    -0.20
    åıijçİ°èĩªå·±
    -0.20
    ä¸Ģæľ¬
    -0.18
     Telegraph
    -0.18
    åĪļåĪļ
    -0.18
    ä¸į说
    -0.18
    第ä¸Ģ
    -0.18
    æĪijåıijçİ°
    -0.17
    è·¨
    -0.17
    POSITIVE LOGITS
     rằng
    0.22
    æľīå¤ļä¹Ī
    0.20
    çļĦåIJįåŃĹ
    0.19
    æ»ĭåij³
    0.19
    æĥħåĨµ
    0.19
    åĹ¥
    0.19
    饽
    0.19
    å§ĵåIJį
    0.19
    ä¼ļéķ¿
    0.18
    æĹºåŃ£
    0.18
    Activations Density 0.064%

    No Known Activations