© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52990
    Prev
    Next
    INDEX
    Explanations

    backgrounds or backgrounds in topics

    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
    æĥ®
    -0.09
    æīĵåĮħ
    -0.09
    Dispatch
    -0.09
    æİĴéĻ¤
    -0.08
    é»ĦçŁ³
    -0.08
    ãģĦãģŁãģł
    -0.08
    ule
    -0.08
    eman
    -0.08
    rtc
    -0.08
    бел
    -0.08
    POSITIVE LOGITS
    èĥĮæĻ¯
    0.17
    åĩºèº«
    0.16
     backgrounds
    0.14
     background
    0.14
     Background
    0.12
    _background
    0.11
     ÑĦон
    0.11
    Background
    0.11
    (background
    0.11
     BACKGROUND
    0.10
    Activations Density 0.075%

    No Known Activations