© 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. 23713
    Prev
    Next
    INDEX
    Explanations

    * punctuation **

    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
    å§Ķ
    -0.09
    æľīåħ´è¶£
    -0.08
    кÑĢа
    -0.08
    راء
    -0.08
    èĭ¥å¹²
    -0.08
    åľ¨å¹¿å·ŀ
    -0.08
     fort
    -0.08
    èIJ¥
    -0.08
    éĤ£æł·çļĦ
    -0.08
    ipe
    -0.08
    POSITIVE LOGITS
    ĶåĽŀ
    0.10
    vox
    0.10
    ÑĦи
    0.09
    _workers
    0.09
    unctuation
    0.09
    éķ¶
    0.09
    amo
    0.09
    cka
    0.09
    arl
    0.09
    uxtap
    0.09
    Activations Density 0.056%

    No Known Activations