© 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. 13650
    Prev
    Next
    INDEX
    Explanations

    on base percentage

    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
    çłĿ
    -0.22
    éĥħ
    -0.22
    ä¸ĢéĹª
    -0.22
    åĬĽæ°Ķ
    -0.20
    äº§åľ°
    -0.19
    åħļåĨħ
    -0.19
    è¿ĻæĶ¯
    -0.18
    -signed
    -0.18
     Mori
    -0.18
    è¶ĬæĿ¥è¶Ĭ大
    -0.18
    POSITIVE LOGITS
    ãģ¾ãģĦ
    0.21
    -git
    0.20
    俳
    0.20
    çİĩ
    0.19
    åĪ°ä½į
    0.19
     tram
    0.18
    dummy
    0.18
    -through
    0.18
    pay
    0.18
     nin
    0.18
    Activations Density 0.001%

    No Known Activations