© 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. 10606
    Prev
    Next
    INDEX
    Explanations

    springboot configuration

    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
    è¢į
    -0.20
    urement
    -0.18
    人士
    -0.18
    langs
    -0.17
    _TER
    -0.16
    è¢Ĥ
    -0.16
    ìĤ¬íķŃ
    -0.16
    åī§ä¸Ń
    -0.15
    UserInfo
    -0.15
    ened
    -0.15
    POSITIVE LOGITS
    ãĤ¬ãĤ¤
    0.20
     HOLDER
    0.19
    fair
    0.18
    rais
    0.18
    cies
    0.18
    girls
    0.18
    ificate
    0.18
    subclass
    0.17
    们
    0.17
    ÑĤа
    0.17
    Activations Density 0.001%

    No Known Activations