© 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. 32165
    Prev
    Next
    INDEX
    Explanations

    should not / select the

    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
    责任æĦŁ
    -0.09
     Rig
    -0.09
    æıIJä¾ĽçļĦ
    -0.09
    oge
    -0.09
     nik
    -0.08
    åłĥ
    -0.08
    ä¹IJè§Ĥ
    -0.08
    oproject
    -0.08
    æ§Ĭ
    -0.08
    .htm
    -0.08
    POSITIVE LOGITS
     Poz
    0.09
    åĭĭ
    0.08
    adden
    0.08
    æľīæĽ´å¥½çļĦ
    0.08
    å¿ħä¸įåı¯
    0.08
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.08
    endas
    0.08
    觥
    0.08
    rod
    0.08
    åĢ¼å¾Ĺä¸Ģ
    0.08
    Activations Density 0.008%

    No Known Activations