© 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. 3242
    Prev
    Next
    INDEX
    Explanations

    arrested or detained

    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
    åħ¶å®ĥéĹ®é¢ĺ
    -0.10
    éķ¿åŁİ
    -0.10
    ToPoint
    -0.10
    ponder
    -0.09
    éĴ¹
    -0.09
    äºĨä¸Ģåı¥
    -0.09
     Chandler
    -0.09
     GAR
    -0.08
    -too
    -0.08
    Ahead
    -0.08
    POSITIVE LOGITS
    æĪIJåĬŁçļĦ
    0.09
     Ske
    0.09
    å°ıå°ıçļĦ
    0.09
    abal
    0.08
    缸åħ³çļĦ
    0.08
    dì
    0.08
    isha
    0.08
    sky
    0.08
    å½ĵæĻļ
    0.08
    ä»Ĭ天çļĦ
    0.08
    Activations Density 0.019%

    No Known Activations