© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51439
    Prev
    Next
    INDEX
    Explanations

    sustained followed by noun or adverbial

    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
    ÑģÑĤеÑĢ
    -0.09
    isa
    -0.08
    resco
    -0.08
    ива
    -0.08
     Tonight
    -0.08
    ç±į
    -0.08
    ../../../
    -0.08
     ÑģлÑĥÑĩаÑı
    -0.08
    深深
    -0.08
    lesia
    -0.08
    POSITIVE LOGITS
    ably
    0.16
    ently
    0.12
    ively
    0.11
    æĢ§çļĦ
    0.11
    ned
    0.10
    enance
    0.10
    ingly
    0.10
    cede
    0.10
    tle
    0.10
    èIJİ
    0.09
    Activations Density 0.011%

    No Known Activations