© 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. 58521
    Prev
    Next
    INDEX
    Explanations

    bye

    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
    常åĬ¡åī¯
    -0.10
    èµĭ
    -0.09
    ipel
    -0.09
    anes
    -0.09
    è®®äºĭ
    -0.09
    屿
    -0.09
    èµ·ä¾Ĩ
    -0.09
    é©®
    -0.09
    kaar
    -0.09
     bÆ°á»Ľc
    -0.09
    POSITIVE LOGITS
    汶
    0.12
    è¿Ļ个ä¸ĸçķĮ
    0.10
    estre
    0.09
    bye
    0.09
    ä¸įå¿ĺ
    0.08
    ç¡®åĪĩ
    0.08
     Editorial
    0.08
    åľ¨è¿Ļç§į
    0.08
    esta
    0.08
    iosis
    0.08
    Activations Density 0.006%

    No Known Activations