© 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. 55610
    Prev
    Next
    INDEX
    Explanations

    body area

    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
    æľīå¾Īå¤ļç§į
    -0.10
    izen
    -0.09
    _OID
    -0.09
    èŀ
    -0.09
    apus
    -0.09
    ä¸įæĸŃå®ĮåĸĦ
    -0.09
    产åĵģè´¨éĩı
    -0.09
    好ä¸į容æĺĵ
    -0.09
    æī¿åĬŀ
    -0.09
    .Stage
    -0.09
    POSITIVE LOGITS
     areas
    0.12
    为éĩįçĤ¹
    0.10
    è¡°éĢĢ
    0.09
    1
    0.08
     entire
    0.08
     area
    0.08
    chen
    0.08
    符åIJĪæĿ¡ä»¶
    0.08
    åħij
    0.08
    ç¬Ļ
    0.08
    Activations Density 0.102%

    No Known Activations