© 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. 1615
    Prev
    Next
    INDEX
    Explanations

    50 fastest Dragons essays

    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
    zeitig
    -0.21
    iton
    -0.20
    ignum
    -0.20
    uming
    -0.20
    mozilla
    -0.20
    outh
    -0.19
    inspace
    -0.19
    INGTON
    -0.19
    night
    -0.19
    åĮ»åѦéĻ¢
    -0.18
    POSITIVE LOGITS
    è¿Ļæł·çļĦè¯Ŀ
    0.20
    atures
    0.19
     liá»ĩu
    0.19
    ãģıãĤĭ
    0.19
    plets
    0.19
    æij¸
    0.18
    ä¸ŃéĢĶ
    0.18
    cip
    0.18
    apore
    0.18
    ths
    0.18
    Activations Density 0.173%

    No Known Activations