© 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. 3509
    Prev
    Next
    INDEX
    Explanations

    you can access

    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
    aim
    -0.09
    å·¥ä½ľæĬ¥åijĬ
    -0.09
    æĮ¥
    -0.08
    ToDevice
    -0.08
    (mode
    -0.08
    æµ®åĬ¨
    -0.08
     Mode
    -0.08
    ев
    -0.08
     satur
    -0.08
     mode
    -0.08
    POSITIVE LOGITS
    ä¸įåĨį
    0.09
    马ä¸Ĭå°±
    0.09
    çĤ¬
    0.08
    ouncer
    0.08
    å¤ļäºĨ
    0.08
    åħ¥åı£
    0.08
    æĶ»åĿļ
    0.08
     tắt
    0.08
    ä¸įèĥ½åĨį
    0.08
    mach
    0.08
    Activations Density 0.024%

    No Known Activations