© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 52203
    Prev
    Next
    INDEX
    Explanations

    first-time usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    itect
    -0.09
    æĿ¥èĩª
    -0.09
    åIJĦåįķä½į
    -0.08
     forcibly
    -0.08
    åĴļ
    -0.08
    icator
    -0.08
    çļĦæĸ¹å¼ıæĿ¥
    -0.08
    裳
    -0.08
    èĩªåѦ
    -0.08
    çĸij
    -0.08
    POSITIVE LOGITS
    è¿ĩå¹´
    0.09
    çī¢
    0.09
    åijĬè¯īä»ĸ
    0.09
    æī§æĶ¿
    0.09
    -run
    0.09
    aires
    0.09
    emax
    0.09
    ernel
    0.09
    åĽ½åĬ¡
    0.08
    縳
    0.08
    Activations Density 0.020%

    No Known Activations