© 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. 48274
    Prev
    Next
    INDEX
    Explanations

    bursts of activity

    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
    顺
    -0.09
    _override
    -0.08
    èĵĵ
    -0.08
    aste
    -0.08
    opol
    -0.08
    pper
    -0.07
    åijĪçİ°åĩº
    -0.07
    é¢Ĩ
    -0.07
    ampton
    -0.07
     trip
    -0.07
    POSITIVE LOGITS
    é¢ĺ主
    0.11
    ä¸Ģéĺµ
    0.11
    ä¸Ģçķª
    0.10
    ä¸įåıĬ
    0.10
    ä¼İ
    0.09
    áĥ£
    0.09
    ä½ķå¿ħ
    0.09
    çĭ¸
    0.09
    çĴĢ
    0.09
    åıĭåĸĦ
    0.09
    Activations Density 0.077%

    No Known Activations