© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12407
    Prev
    Next
    INDEX
    Explanations

    insurance, health, coffee, mortgage, tour, railway, industrial

    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
    ¢åįķ
    -0.18
    orsche
    -0.17
    èĿĮ
    -0.17
    BILE
    -0.17
    ä¸¥æł¼çļĦ
    -0.17
    åįķ纯çļĦ
    -0.17
     же
    -0.17
    än
    -0.17
    gressive
    -0.17
    褡
    -0.17
    POSITIVE LOGITS
    æľīéĻIJåħ¬åı¸
    0.20
    骧
    0.19
    @yahoo
    0.19
    è¿Ļ家åħ¬åı¸
    0.18
    ®,
    0.18
    ®
    0.17
    IFE
    0.17
    stime
    0.17
    Suit
    0.17
    artic
    0.17
    Activations Density 0.331%

    No Known Activations