© 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. 21922
    Prev
    Next
    INDEX
    Explanations

    names and entities

    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
    eners
    -0.09
    entic
    -0.09
    ores
    -0.09
    prises
    -0.09
    ally
    -0.09
    isode
    -0.09
     Conserv
    -0.09
     sobie
    -0.08
    pping
    -0.08
     ÐŁÐ¾Ñĩем
    -0.08
    POSITIVE LOGITS
    ../../../
    0.12
    olk
    0.09
    ä¿©
    0.09
    ìļ±
    0.09
    æĥķ
    0.09
    è¿ĻäºĽéĥ½æĺ¯
    0.09
    ses
    0.09
    reed
    0.09
    èĥ½å¾ĹåĪ°
    0.08
    town
    0.08
    Activations Density 0.012%

    No Known Activations