© 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. 1927
    Prev
    Next
    INDEX
    Explanations

    location, date, and announcement

    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
    è¿ijå¹´
    -0.28
    åŃ£åIJİ
    -0.26
    è¿ijåĩłå¹´
    -0.26
     yearly
    -0.25
    åIJĮç±»
    -0.24
    ç»ıéªĮåĴĮ
    -0.24
    æĺ¥èĬĤæľŁéĹ´
    -0.23
    éĥ½æľīèĩªå·±
    -0.23
    说å®Į
    -0.23
    åIJĮæľŁ
    -0.23
    POSITIVE LOGITS
     Everywhere
    0.24
    è®°èĢħ
    0.23
     —
    0.23
    çľ¼æ³ª
    0.23
     Noble
    0.22
     Printing
    0.22
     reporters
    0.22
    åŃļ
    0.22
     z
    0.21
     reporter
    0.21
    Activations Density 0.021%

    No Known Activations