© 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. 15124
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions

    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
     chap
    -0.21
    ãĢģ
    -0.20
     momentum
    -0.19
    ri
    -0.19
    ä¼´
    -0.18
    å®ģéĿĻ
    -0.18
    çİ°
    -0.18
    åIJĮæŶ
    -0.18
    ä½Ľ
    -0.17
     delt
    -0.17
    POSITIVE LOGITS
    éħĮ
    0.21
    æ¯Ķäºļ
    0.20
     móvil
    0.20
    -tm
    0.20
    èIJ½ä¸ĭ
    0.20
    eselect
    0.19
    تأسÙĬ
    0.19
    stad
    0.19
    èĹĵ
    0.19
     Essen
    0.19
    Activations Density 0.001%

    No Known Activations