© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2797
    Prev
    Next
    INDEX
    Explanations

    patch files or code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    åĮħåIJ«äºĨ
    -0.25
    奥è¿IJ
    -0.24
    大夫
    -0.23
     meg
    -0.22
     mas
    -0.22
    éĺľ
    -0.22
    ä¾ĭè¡Į
    -0.22
     potentially
    -0.22
     hyper
    -0.22
    ä¼łè¨Ģ
    -0.22
    POSITIVE LOGITS
    ·»
    0.26
    èĬ³é¦Ļ
    0.25
     Followers
    0.24
     Replies
    0.24
    ighton
    0.23
    uzu
    0.22
    éħ¶
    0.21
    uzzi
    0.21
     ['',
    0.21
     Patton
    0.21
    Activations Density 0.001%

    No Known Activations