© 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. 11590
    Prev
    Next
    INDEX
    Explanations

    Untitled, Form, New, Application, Unnamed, Model

    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
    ponsored
    -0.21
    ubar
    -0.20
     Douglas
    -0.18
    æł¸å¿ĥåĮº
    -0.18
     Mori
    -0.18
     ÐIJлекÑģан
    -0.18
    /car
    -0.18
    çĿĢä»ĸ
    -0.18
    illion
    -0.18
    ç¿ķ
    -0.17
    POSITIVE LOGITS
    æ®ĸ
    0.21
    Unnamed
    0.21
    acci
    0.20
    è¿Ļ两个
    0.19
    ÑĤÑĢо
    0.18
    umd
    0.18
     traumatic
    0.17
    ç¼ľ
    0.17
    lli
    0.17
    åĪĩåī²
    0.17
    Activations Density 0.199%

    No Known Activations