© 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. 52456
    Prev
    Next
    INDEX
    Explanations

    yahoo, license, company names

    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
    微信群
    -0.12
    Æ°ng
    -0.09
    eprom
    -0.09
    å¢Ļä¸Ĭ
    -0.09
     Fraser
    -0.09
    æ¡ĮåŃIJä¸Ĭ
    -0.09
    忱
    -0.09
    èģĶç³»çĶµè¯Ŀ
    -0.09
    颦
    -0.09
    ãģ£ãģ±
    -0.08
    POSITIVE LOGITS
    Yahoo
    0.11
    yahoo
    0.10
     Splash
    0.10
    .yahoo
    0.10
    inqu
    0.10
    ockey
    0.09
    æIJľ
    0.09
    æµģéĩı
    0.09
    Messenger
    0.09
    éĴĵé±¼
    0.09
    Activations Density 0.069%

    No Known Activations