© 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. 32762
    Prev
    Next
    INDEX
    Explanations

    any other

    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
    妪
    -0.09
    åĮħåĮħ
    -0.09
    inheritDoc
    -0.09
    æľīä¸Ģå®ļçļĦ
    -0.09
    çĪ±ä¸Ĭ
    -0.09
    è¿Ļæīįæĺ¯
    -0.09
    åĬłå¼ºå¯¹
    -0.08
    ysi
    -0.08
    å°½åı¯èĥ½
    -0.08
    clf
    -0.08
    POSITIVE LOGITS
    伯
    0.09
    bing
    0.09
    çķ´
    0.09
    oola
    0.09
    ç½®äºİ
    0.08
     Äijá»ĩ
    0.08
    ä¸įä¼ļåĨį
    0.08
    åľ°ä¸Ń
    0.08
    ApiClient
    0.08
    ding
    0.08
    Activations Density 0.171%

    No Known Activations