© 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. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 2610
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

    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
    INET
    -0.25
     Curtain
    -0.25
    èĮ¬
    -0.25
    åIJ¹
    -0.23
    ASCADE
    -0.23
    èζ
    -0.23
    -football
    -0.22
     Champ
    -0.22
    ascade
    -0.21
    ivec
    -0.21
    POSITIVE LOGITS
    -clear
    0.25
    çºłéĶĻ
    0.24
     Learn
    0.24
    åѦä¼ļ
    0.23
    导读
    0.23
    è®¤çľŁåŃ¦ä¹ł
    0.23
    lessness
    0.22
    æIJĤ
    0.22
    çŁ¥éģĵèĩªå·±
    0.22
    人类
    0.22
    Activations Density 0.001%

    No Known Activations