© 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. 27499
    Prev
    Next
    INDEX
    Explanations

    Carlton Place / Tower / Group

    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
    å©¿
    -0.10
    嵩
    -0.09
    ä¸»åľº
    -0.09
    éĴ¼
    -0.09
    itics
    -0.08
    示æĦı
    -0.08
    mund
    -0.08
    ä¸ŃåĽ½å¤§éĻĨ
    -0.08
    æľºéģĩ
    -0.08
    arend
    -0.08
    POSITIVE LOGITS
    ablish
    0.09
    嵬
    0.08
    çªģ
    0.08
    anter
    0.08
    OfFile
    0.08
    æĬ«éľ²
    0.08
    ugged
    0.08
    ed
    0.08
    è¹Ĥ
    0.08
    æ´¹
    0.08
    Activations Density 0.004%

    No Known Activations