© 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. 21591
    Prev
    Next
    INDEX
    Explanations

    center of

    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¤ļåľ°
    -0.09
    ruk
    -0.08
    åIJĦåľ°
    -0.08
    _icons
    -0.08
     spur
    -0.08
    å¤ĸçķĮ
    -0.08
    eyJ
    -0.08
    稳åģ¥
    -0.08
    SIM
    -0.08
    ableView
    -0.07
    POSITIVE LOGITS
    辫
    0.12
    å·¥ç¨ĭé¡¹çĽ®
    0.11
    éĤ£ä»½
    0.11
    izer
    0.10
    izers
    0.10
    most
    0.10
    åºŃ
    0.09
    åĶ§
    0.09
    æļ´é£İ
    0.09
    éĥ¨ä½į
    0.09
    Activations Density 0.042%

    No Known Activations