© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11310
    Prev
    Next
    INDEX
    Explanations

    names in sports contexts

    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
    å·į
    -0.20
    æ§Į
    -0.20
    æĪIJéķ¿
    -0.20
    æĪIJéķ·
    -0.19
    ç¿İ
    -0.19
    éķ¿å¤§
    -0.19
    åıijå±ķ壮大
    -0.18
    ç¨ļ
    -0.18
    kes
    -0.18
    .saved
    -0.18
    POSITIVE LOGITS
    临æŶ
    0.21
    çļĦåĪ°æĿ¥
    0.20
    å
    0.19
    éĽĩä½£
    0.19
    éĽĨåĽ¢åħ¬åı¸
    0.19
     Extras
    0.19
    åĿı
    0.18
    æĻķ
    0.18
    çĶŁæĢģåľĪ
    0.18
    å°¾
    0.18
    Activations Density 0.024%

    No Known Activations