© 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. 9837
    Prev
    Next
    INDEX
    Explanations

    Copyright or game related

    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
    åĽ¡
    -0.10
    unded
    -0.09
    欢åĸľ
    -0.08
    æīª
    -0.08
    é¢Ħç®Ĺ
    -0.08
    åħ¥å¸Ĥ
    -0.08
    社åĮº
    -0.08
    ÑĢок
    -0.08
     neighborhood
    -0.08
     Neighborhood
    -0.07
    POSITIVE LOGITS
    èµĮåľº
    0.10
    swiper
    0.09
    å¦ĵ
    0.09
     ÐIJна
    0.09
    娼
    0.09
    bah
    0.09
     Casino
    0.09
     Roulette
    0.09
    _SHA
    0.09
    çĸĹ
    0.09
    Activations Density 0.042%

    No Known Activations