© 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. 49090
    Prev
    Next
    INDEX
    Explanations

    days of the week followed by time

    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
    æŁĦ
    -0.09
    åįıåĬŀ
    -0.08
    athe
    -0.08
    顺便
    -0.08
    èĤĦ
    -0.07
    raits
    -0.07
    zá
    -0.07
     Gors
    -0.07
    spm
    -0.07
    æ©Ħæ¦Ħ
    -0.07
    POSITIVE LOGITS
    以人æ°ij
    0.09
    ä¸īä½įä¸Ģä½ĵ
    0.09
    å¦Ĥæŀľä¸įæĺ¯
    0.09
    илÑĮно
    0.08
    éģº
    0.08
    /release
    0.08
    atically
    0.08
    udio
    0.08
    åľ¨å¸Ĥåľºä¸Ĭ
    0.08
    读åIJİ
    0.08
    Activations Density 0.035%

    No Known Activations