© 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. 56187
    Prev
    Next
    INDEX
    Explanations

    polymer preparation and methods

    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
    ols
    -0.09
    pressed
    -0.08
    inox
    -0.08
    -wheel
    -0.08
    anj
    -0.08
     Shel
    -0.08
    缴æĴŃ
    -0.08
     NM
    -0.08
     past
    -0.08
    à¸Īำà¸ģ
    -0.08
    POSITIVE LOGITS
    æ´ĹèĦ¸
    0.10
    alic
    0.09
     Ñĩел
    0.09
    æĵį纵
    0.09
    åĤĢ
    0.09
    éĥ§
    0.09
    è®®äºĭ
    0.09
    ä¼ļéķ¿
    0.09
    ÑģÑĮ
    0.09
    æĹ¥è®¯
    0.09
    Activations Density 0.168%

    No Known Activations