© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 32262
    Prev
    Next
    INDEX
    Explanations

    specific days of the week

    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
    inel
    -0.11
    неÑĤ
    -0.10
    ç¼ľ
    -0.09
    ../../
    -0.09
    ../../../
    -0.09
    aos
    -0.09
    ation
    -0.09
    alyze
    -0.09
    åĿĤ
    -0.09
    oval
    -0.09
    POSITIVE LOGITS
    nd
    0.11
    lijk
    0.11
    ä¸īåĽĽ
    0.09
    lijke
    0.09
    æ±°
    0.09
    upy
    0.09
    otte
    0.08
     dục
    0.08
    -thirds
    0.08
    ³
    0.08
    Activations Density 0.014%

    No Known Activations