© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 10911
    Prev
    Next
    INDEX
    Explanations

    after condition or event

    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
    ç¬Ķè®°
    -0.22
    ä½łçİ°åľ¨
    -0.20
    omi
    -0.20
    YO
    -0.19
    ä¸įè¶³
    -0.18
    resco
    -0.18
    éͤ
    -0.18
    æĽ©
    -0.18
    ç¥ŀéĢļ
    -0.18
    è¶ĬæĿ¥è¶Ĭ大
    -0.18
    POSITIVE LOGITS
    åħĪ
    0.31
    åħĪè¡Į
    0.28
    åħĪæĬĬ
    0.27
     ÙĪØ¨Ø¹Ø¯
    0.25
    åIJİåĨį
    0.22
    åģļå®Į
    0.21
    èµ·çłģ
    0.21
    çľĭå®Į
    0.20
     먼ìłĢ
    0.20
    ç¡®åĪĩ
    0.20
    Activations Density 0.047%

    No Known Activations