© 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. 34747
    Prev
    Next
    INDEX
    Explanations

    few studies/data/cases

    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
    æľīæŶåĢĻ
    -0.08
    大å°ı
    -0.08
    æŁIJç§į
    -0.08
    诰
    -0.08
    åIJĪçIJĨçļĦ
    -0.08
    ç¼®
    -0.08
    å¿ĥçIJĨåĴ¨è¯¢
    -0.08
    çī¹æľĹ
    -0.07
    éĿŀ常éĩįè¦ģ
    -0.07
    å¾Īéĩįè¦ģ
    -0.07
    POSITIVE LOGITS
     actually
    0.11
     вообÑīе
    0.11
    羣æŃ£
    0.11
     glam
    0.10
    ROOT
    0.10
    èħ³
    0.10
     actual
    0.10
    èĦļ
    0.10
    ä¾ĭå¤ĸ
    0.10
    çĶļèĩ³
    0.10
    Activations Density 0.125%

    No Known Activations