© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47761
    Prev
    Next
    INDEX
    Explanations

    now is the 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
    related
    -0.09
     Tops
    -0.08
    èµ·åĪĿ
    -0.08
    ä¿Ŀå®ļ
    -0.08
    room
    -0.08
    ÐĺÐĿ
    -0.08
    missing
    -0.07
    æĸĽ
    -0.07
    ä¸Ģå¼Ģå§ĭ
    -0.07
    æĭŁ
    -0.07
    POSITIVE LOGITS
    主ä¹īèĢħ
    0.11
    abouts
    0.10
    æľ
    0.10
    æŶåĢĻ
    0.10
    çĦ±
    0.10
    èĪĮå°ĸ
    0.10
    eries
    0.09
    ledge
    0.09
    æľīä»»ä½ķ
    0.09
    æĻĤåĢĻ
    0.09
    Activations Density 0.008%

    No Known Activations