© 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. 58065
    Prev
    Next
    INDEX
    Explanations

    mon/mono prefixes

    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
    ÙĦÙĤ
    -0.10
    ä¼ı
    -0.10
    ÑĨин
    -0.09
    ionario
    -0.09
    ãĥIJãĥª
    -0.09
    orian
    -0.09
    çĹĴ
    -0.09
    èķ¨
    -0.09
    åŁļ
    -0.09
    _MIDDLE
    -0.08
    POSITIVE LOGITS
     mon
    0.11
    æįĨç»ij
    0.10
    (mon
    0.09
    æŁ¬
    0.09
     mono
    0.09
     Mono
    0.09
    å¼ıçļĦ
    0.09
    ument
    0.09
    æ¡ī
    0.08
    Mono
    0.08
    Activations Density 0.025%

    No Known Activations