© 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. 10922
    Prev
    Next
    INDEX
    Explanations

    racing seasons and events

    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
    åĩºå¤Ħ
    -0.20
    á¿ĸ
    -0.20
    etto
    -0.19
    ç«Ļéķ¿
    -0.19
    NamedQuery
    -0.18
    .press
    -0.18
     decom
    -0.18
    ered
    -0.18
    游æĪı代
    -0.18
    ackers
    -0.17
    POSITIVE LOGITS
    京åŁİ
    0.23
    çĭ¬ç«ĭ
    0.23
    ä½ĵç³»
    0.21
    æłĩåĩĨ
    0.21
     Tear
    0.20
    èµ·æŃ¥
    0.20
    ç±»åĪ«
    0.20
    çģ¯åħī
    0.20
    宽
    0.20
    æ¯ķä¸ļåIJİ
    0.19
    Activations Density 0.022%

    No Known Activations