© 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. 48785
    Prev
    Next
    INDEX
    Explanations

    media press events

    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
    pio
    -0.09
    åħ¥ãĤĬ
    -0.09
    ç¾İ人
    -0.09
     Glock
    -0.09
    çīĩåĪ»
    -0.08
    IVO
    -0.08
    éĴª
    -0.08
    éħŀ
    -0.08
    keeper
    -0.08
     miscellaneous
    -0.08
    POSITIVE LOGITS
    人åijĺ
    0.11
    人åĵ¡
    0.10
    æį»
    0.09
     Revel
    0.08
    ầy
    0.08
    åѤ
    0.08
    转让
    0.08
     зав
    0.08
     Wolff
    0.08
    ä¼ijæģ¯
    0.08
    Activations Density 0.013%

    No Known Activations