© 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. 33052
    Prev
    Next
    INDEX
    Explanations

    only

    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
     Ple
    -0.09
    å°Ĩèĩªå·±çļĦ
    -0.08
    æĹ¢æĺ¯
    -0.08
    游ä¹IJ
    -0.08
    alto
    -0.08
    æĸĩåĮĸåºķèķ´
    -0.08
    éĢĤ
    -0.08
     Sor
    -0.08
    ä¸įä»ħ
    -0.08
    ongo
    -0.08
    POSITIVE LOGITS
    èĢĮå·²
    0.18
     alone
    0.18
    alone
    0.17
    ãģłãģij
    0.17
     saja
    0.17
    -only
    0.16
     Alone
    0.15
     thôi
    0.14
    ë§Į
    0.14
    ãģ®ãģ¿
    0.14
    Activations Density 0.363%

    No Known Activations