© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15101
    Prev
    Next
    INDEX
    Explanations

    .com, email addresses, URLs, python, court

    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
    ISODE
    -0.20
    æľ¬ç½ijç«Ļ
    -0.20
    ensively
    -0.20
    va
    -0.19
    bens
    -0.19
    ups
    -0.18
    çĨ¨
    -0.18
    çīĽ
    -0.18
    _LOOK
    -0.18
    anguages
    -0.18
    POSITIVE LOGITS
    æĬķ
    0.21
    éĤ®å¯Ħ
    0.20
     Collector
    0.19
    åįķä¸Ģ
    0.19
    amt
    0.19
    anova
    0.19
    è¿Īè¿Ľ
    0.19
    collector
    0.18
    æľīä»»ä½ķ
    0.18
    çªį
    0.18
    Activations Density 0.019%

    No Known Activations