© 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. 17115
    Prev
    Next
    INDEX
    Explanations

    materials adjectives

    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
     Bowling
    -0.21
    åij½
    -0.20
    hood
    -0.20
    hoe
    -0.19
     Jed
    -0.19
     Laden
    -0.19
    à¹ĭ
    -0.19
    hoff
    -0.18
    /how
    -0.18
    /desktop
    -0.18
    POSITIVE LOGITS
     dÆ°
    0.20
    æĬĢæľ¯åĴĮ
    0.20
    çĴľ
    0.20
    éĴ¢æĿ¿
    0.19
    ç²¾éĢī
    0.19
    ãĥ¼ãĥ³
    0.19
    å®ĮåĸĦçļĦ
    0.19
    ç»ij
    0.19
    stone
    0.18
    askan
    0.18
    Activations Density 0.159%

    No Known Activations