© 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. 16509
    Prev
    Next
    INDEX
    Explanations

    title of a work

    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
    èĢĨ
    -0.26
     nostalg
    -0.20
    è¸Ĭ
    -0.20
    $input
    -0.20
    untu
    -0.20
     Seas
    -0.20
     Parade
    -0.20
    èĬĿ
    -0.20
    opard
    -0.19
    æģ¼
    -0.19
    POSITIVE LOGITS
    sss
    0.22
    年级
    0.22
    ç½ij讯
    0.21
     Tumblr
    0.20
    çIJĨæĻº
    0.20
    å®īåħ¨ç®¡çIJĨ
    0.20
    åĬłå·¥åİĤ
    0.19
     POV
    0.19
    atu
    0.19
     DISCLAIMER
    0.19
    Activations Density 0.104%

    No Known Activations