© 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. 48877
    Prev
    Next
    INDEX
    Explanations

    struggles with money or boredom

    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
    ç»Ļä½łä»¬
    -0.10
    ä¸Ĭä¸ĭ游
    -0.09
    éĤ£æŶ
    -0.09
    åijĬè¯īæĪij
    -0.09
    éĶģå®ļ
    -0.09
    æĪij们ä¼ļ
    -0.09
    éĹ®æĪij
    -0.09
    æĪij说
    -0.09
    à§į
    -0.09
    使æĪij
    -0.08
    POSITIVE LOGITS
    èµĬ
    0.10
    .Callback
    0.09
    igm
    0.08
     Royale
    0.08
     titular
    0.08
    æĹłäºº
    0.08
    åĦĴ
    0.08
    äºĨä»ĸçļĦ
    0.08
    gil
    0.08
     POV
    0.07
    Activations Density 0.288%

    No Known Activations