© 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. 7282
    Prev
    Next
    INDEX
    Explanations

    day of the week or month

    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
    ä¸įçķĻ
    -0.11
     Gum
    -0.10
    èµ°ä¸ĭåİ»
    -0.09
    isman
    -0.09
    sic
    -0.09
    çĦ¶
    -0.09
    èĭ´
    -0.09
    ÑĩаÑĤ
    -0.09
    oge
    -0.09
    å¥Ķ
    -0.09
    POSITIVE LOGITS
    /posts
    0.09
    utters
    0.09
    åĴĮå®ĮåĸĦ
    0.09
    æĵ
    0.08
     brushes
    0.08
    ä¼ij
    0.08
    æľīå¤ļ
    0.08
    åĴĮæĶ¯æĮģ
    0.08
    æĩĴ
    0.08
    antz
    0.08
    Activations Density 0.040%

    No Known Activations