© 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. 12535
    Prev
    Next
    INDEX
    Explanations

    detection, frosting, introduction, coupe, sort

    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
    èIJ½åľ°
    -0.23
    æŁĦ
    -0.22
    æľĢæĹ©çļĦ
    -0.19
    ì±Ħ
    -0.18
    å¿ĥæĢģ
    -0.18
    æĶ¸
    -0.18
    aris
    -0.18
    缮çĿ¹
    -0.18
    ç«ĭæ¡Ī
    -0.18
    nod
    -0.18
    POSITIVE LOGITS
    ÙĪÙĦÙĬ
    0.20
    ç½²
    0.19
    åĿĬ
    0.19
    REN
    0.19
    ä¼Łå¤§
    0.19
    çļĦè§ĤçĤ¹
    0.19
    pagen
    0.18
     seper
    0.18
     Omni
    0.17
    åĴĮæľįåĬ¡
    0.17
    Activations Density 0.001%

    No Known Activations