© 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. 2740
    Prev
    Next
    INDEX
    Explanations

    explaining or defining concepts

    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
    å¸ĸ
    -0.23
    anker
    -0.22
    RANDOM
    -0.22
    ivas
    -0.22
    {},↵
    -0.22
    hra
    -0.21
    hare
    -0.21
    Tam
    -0.21
    æĬĢæľ¯åĴĮ
    -0.21
    #undef
    -0.21
    POSITIVE LOGITS
    ´t
    0.23
    ksz
    0.21
    -setup
    0.21
    \xc
    0.21
     Â
    0.21
    ä¼
    0.21
     Petsc
    0.21
    éºĿ
    0.20
    odore
    0.20
    ãģıãĤĭ
    0.20
    Activations Density 0.187%

    No Known Activations