© 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. 22623
    Prev
    Next
    INDEX
    Explanations

    wound up

    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
    ä¼łæĴŃ
    -0.09
     Agility
    -0.09
    ä¿®åħ»
    -0.09
    ä¼łæĿ¥
    -0.09
    æĭīæĸ¯
    -0.09
    åĢ¾
    -0.09
    æĢ»éĺŁ
    -0.08
    åĨĽå®ĺ
    -0.08
    åŀ«
    -0.08
    dimension
    -0.08
    POSITIVE LOGITS
    ry
    0.10
    à´Ļ
    0.09
    aries
    0.09
    robe
    0.09
    hea
    0.09
    hana
    0.09
    rim
    0.09
    éļ¾åħį
    0.09
    alis
    0.08
    reich
    0.08
    Activations Density 0.008%

    No Known Activations