© 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. 17173
    Prev
    Next
    INDEX
    Explanations

    OAuth 2.0

    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
    Negative Logits
    å½ĸ
    -0.20
    iram
    -0.19
    queeze
    -0.18
    被åĬ¨
    -0.18
    inker
    -0.17
     Modifier
    -0.17
    .Sm
    -0.17
    åħļåĨħ
    -0.17
    utch
    -0.17
    _MAPPING
    -0.17
    POSITIVE LOGITS
    ç¢İ
    0.19
    ogenerated
    0.19
    jal
    0.18
    åªĴ
    0.18
    å®ĺæĸ¹å¾®åįļ
    0.17
    å®ĺç½ij
    0.17
    lover
    0.17
    æ¹®
    0.17
    ä¹Łå¾Ī
    0.17
    &o
    0.17
    Activations Density 0.007%

    No Known Activations