© 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. 55392
    Prev
    Next
    INDEX
    Explanations

    embark on

    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
    çļĦè¡£æľį
    -0.09
    ocation
    -0.09
    nelle
    -0.09
    coon
    -0.09
    irth
    -0.08
    å¼Ģå¥ĸ
    -0.08
    anuts
    -0.08
    åIJĦæĸ¹
    -0.08
    é¦ĸåĪĽ
    -0.08
    andro
    -0.08
    POSITIVE LOGITS
    æĸ°å¾ģç¨ĭ
    0.11
    ä¸ºæľŁ
    0.10
    æĸ°ä¸Ģè½®
    0.10
    å¾ģç¨ĭ
    0.10
    hamster
    0.10
    isphere
    0.10
    rial
    0.10
    æĸ°çļĦä¸Ģ
    0.10
    ä¹ĭæĹħ
    0.10
    æĹħç¨ĭ
    0.09
    Activations Density 0.007%

    No Known Activations