© 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. 1933
    Prev
    Next
    INDEX
    Explanations

    sequences of wins or losses

    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
    Delegate
    -0.25
    pone
    -0.24
    Role
    -0.24
    Typed
    -0.22
     GdaÅĦsk
    -0.22
     roleName
    -0.22
    Speed
    -0.22
     Kel
    -0.22
     Reed
    -0.22
     Rates
    -0.21
    POSITIVE LOGITS
     consecutive
    0.51
     consec
    0.44
    è¿ŀç»Ń
    0.42
     longest
    0.40
     streak
    0.39
    æľĢéķ¿
    0.38
    è¿ŀèĥľ
    0.37
    éķ¿è¾¾
    0.36
     uninterrupted
    0.36
     stretches
    0.36
    Activations Density 0.038%

    No Known Activations