© 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. 13625
    Prev
    Next
    INDEX
    Explanations

    acoustic rhinometry, Medicare, Barber, erysipelas

    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
    稽
    -0.22
    ç¥ĸ
    -0.21
    bring
    -0.21
    æ¶İ
    -0.20
    ob
    -0.19
    printStats
    -0.18
    éļıåIJİ
    -0.18
    berger
    -0.17
    acci
    -0.17
    .comm
    -0.17
    POSITIVE LOGITS
    è¹Ļ
    0.20
    ĸ
    0.20
    åij¸
    0.20
    縱
    0.20
    èĥģ
    0.20
    使çĶ¨çļĦ
    0.20
    æĶ¯æŁ±
    0.19
    使èĢħ
    0.19
    纵
    0.18
    åĽ´è§Ĥ
    0.18
    Activations Density 1.707%

    No Known Activations