© 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. 22548
    Prev
    Next
    INDEX
    Explanations

    makeover, wake up call, extra kick

    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
    reten
    -0.09
     Paw
    -0.09
     Spread
    -0.09
    èĿī
    -0.09
    欢
    -0.09
    alars
    -0.08
    å¾Īåĸľæ¬¢
    -0.08
    弦
    -0.08
    æĸ°äºº
    -0.08
     StringTokenizer
    -0.08
    POSITIVE LOGITS
    æĹ¢
    0.11
    æ´Ĺ礼
    0.10
    åįĪ
    0.10
     Sne
    0.09
    æľīåħ³éĥ¨éŨ
    0.09
    çĭłçĭł
    0.08
    çĽ¹
    0.08
    èĢĥéªĮ
    0.08
    .axes
    0.08
    æľºä¼ļ
    0.08
    Activations Density 0.160%

    No Known Activations