© 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. 13049
    Prev
    Next
    INDEX
    Explanations

    Guinness World Records

    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
    è½²
    -0.20
    ç½ijç«Ļåľ°åĽ¾
    -0.19
    .netbeans
    -0.19
     combinations
    -0.19
    -collapse
    -0.18
    ERM
    -0.18
    ç»ĦåIJĪ
    -0.18
    CHASE
    -0.17
    GetInstance
    -0.17
    _COLL
    -0.17
    POSITIVE LOGITS
     Guinness
    0.25
    è®°è½½
    0.22
    æ±Ĺæ°´
    0.21
    ä¸ŃåĽ½æĸĩåĮĸ
    0.20
     Tem
    0.20
    èĬĤ
    0.20
    纪å½ķ
    0.20
    verse
    0.19
    纬
    0.19
    ç±»åĪ«
    0.19
    Activations Density 0.006%

    No Known Activations