© 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. 17042
    Prev
    Next
    INDEX
    Explanations

    side 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
    ä¹į
    -0.10
    骡
    -0.09
    åĨĪ
    -0.09
    æµĭè¯Ħ
    -0.09
    êt
    -0.08
    èĢĥè¯Ħ
    -0.08
    SCI
    -0.08
    ucceeded
    -0.08
    enis
    -0.08
    å¡ŀå°Ķ
    -0.08
    POSITIVE LOGITS
    è¿Ļè¾¹
    0.13
    æĸ¹éĿ¢çļĦ
    0.11
    æĸ¹éĿ¢
    0.11
    ä¸ĢéĿ¢
    0.10
     side
    0.10
     aspects
    0.10
    ä¼´ä¾£
    0.09
    åı¦ä¸Ģè¾¹
    0.09
    stuff
    0.09
    éĤ£è¾¹
    0.09
    Activations Density 0.022%

    No Known Activations