© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6678
    Prev
    Next
    INDEX
    Explanations

    user profiles

    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
    oftware
    -0.09
    空ä¸Ń
    -0.09
     ÙĪعد
    -0.09
    оÑĢдин
    -0.08
    â§
    -0.08
    _ING
    -0.08
    ÑĪи
    -0.08
    _cid
    -0.08
     MANUAL
    -0.08
     Hands
    -0.08
    POSITIVE LOGITS
    丰满
    0.12
    页éĿ¢
    0.11
    åĴĮ个人
    0.10
    ä¸Ģ页
    0.10
    认
    0.10
    ç«ĭãģ¡
    0.10
    æīĢæľī人
    0.09
    æķ´ä¸ªäºº
    0.09
    éĥ¨èIJ½
    0.09
    åºĹéĵº
    0.09
    Activations Density 0.085%

    No Known Activations