© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10687
    Prev
    Next
    INDEX
    Explanations

    said by

    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
    zek
    -0.20
     Pacers
    -0.18
    ertz
    -0.18
    æĪijä¸įæĺ¯
    -0.18
    ç§į
    -0.18
    iking
    -0.18
    iban
    -0.17
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.17
     Raqqa
    -0.17
     Vinci
    -0.17
    POSITIVE LOGITS
    æĹ¶è¡¨ç¤º
    0.23
    åªĴä½ĵ
    0.22
    æľ¬ç½ij
    0.22
    è®°èĢħ表示
    0.21
    大家åĪĨ享
    0.19
    åıĹå½±åĵį
    0.19
    åīįè¿°
    0.19
    owed
    0.19
    宪
    0.19
    nees
    0.18
    Activations Density 0.014%

    No Known Activations