© 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. 20116
    Prev
    Next
    INDEX
    Explanations

    starting a sentence with "as", "one", "this", etc

    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
    çļĦè¯Ŀ
    -0.08
     ÂŃ
    -0.08
    代åĬŀ
    -0.08
    ÄĻ
    -0.07
     and
    -0.07
    å°Ĩæĺ¯
    -0.07
    æĹĦ
    -0.07
     Pur
    -0.07
    olar
    -0.07
    éĿ
    -0.07
    POSITIVE LOGITS
    ä¸ĢåŃĹ
    0.11
    è°¯
    0.10
    åħ·ä½ĵ
    0.09
    -scrollbar
    0.09
    ÐľÐŀ
    0.09
    GridColumn
    0.09
    astreet
    0.09
    åİŁåĽłæĺ¯
    0.09
    /rs
    0.09
    roma
    0.09
    Activations Density 1.051%

    No Known Activations