© 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. 2556
    Prev
    Next
    INDEX
    Explanations

    apparatus, devices, systems, tools, factors, procedures

    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
    amba
    -0.09
    Ãłnh
    -0.08
    åѦåĪ°
    -0.08
    天ä¸ĭ
    -0.08
    æĺ¯æĪijåĽ½
    -0.08
    æ¶ī
    -0.08
    æĬĹçĻĮ
    -0.08
    éĢģåĩº
    -0.08
    åıĹçĽĬ
    -0.08
    meer
    -0.07
    POSITIVE LOGITS
    åĴĮæĬĢæľ¯
    0.17
    åı¯ä»¥å¸®åĬ©
    0.11
    åĨ¢
    0.11
    æĬĢæľ¯æĶ¯æĮģ
    0.10
    æľīæķĪåľ°
    0.10
    apo
    0.09
    ardo
    0.09
    åĴĮæľįåĬ¡
    0.09
    åı¯ä»¥èİ·å¾Ĺ
    0.08
     szkoÅĤy
    0.08
    Activations Density 0.642%

    No Known Activations