© 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. 10642
    Prev
    Next
    INDEX
    Explanations

    status quo

    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
     Attribution
    -0.10
    ä¸ĢæľŁ
    -0.09
    ç´¯äºĨ
    -0.09
     PIT
    -0.09
    åĽĽåŃ£
    -0.09
    åĢ©
    -0.09
    otta
    -0.08
    ë³µ
    -0.08
    erer
    -0.08
    è¿Ļ个ä¸ĸçķĮ
    -0.08
    POSITIVE LOGITS
     quo
    0.10
    å¤Ł
    0.09
    inton
    0.09
     ÑģовеÑĤ
    0.09
    ä½İåİĭ
    0.08
    å«ģ
    0.08
    ãĤĿ
    0.08
    æĻļé¤IJ
    0.08
    =status
    0.08
    langs
    0.08
    Activations Density 0.017%

    No Known Activations