© 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. 19678
    Prev
    Next
    INDEX
    Explanations

    United Kingdom

    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
    agues
    -0.10
    天ä¸ĭ
    -0.09
    åIJijå¾Ģ
    -0.09
    ä¸ŃåĽ½è¶³çIJĥ
    -0.09
    thal
    -0.09
    vens
    -0.09
    umas
    -0.08
    tık
    -0.08
    çľģæĶ¿åºľ
    -0.08
    heit
    -0.08
    POSITIVE LOGITS
    åIJĮèĥŀ
    0.12
    佬
    0.11
    -wide
    0.10
    å·¥ä½ľèĢħ
    0.10
    nowledge
    0.10
    çļĦéĴ±
    0.10
    wide
    0.10
    æľ¬åľŁ
    0.10
    -born
    0.10
    æĬĬè¿Ļ个
    0.09
    Activations Density 0.019%

    No Known Activations