© 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. 36193
    Prev
    Next
    INDEX
    Explanations

    Putin's Russia

    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
    ué
    -0.10
    é¼ĵ
    -0.08
    ảnh
    -0.08
    ening
    -0.08
    uku
    -0.08
    afen
    -0.08
    ened
    -0.08
    å°Ĭ
    -0.08
    èºħ
    -0.08
     strain
    -0.08
    POSITIVE LOGITS
    éĿŀ常åĸľæ¬¢
    0.09
    ä¾
    0.09
    ovie
    0.09
    æ§ģ
    0.09
    鸱
    0.09
    建çŃijæĿIJæĸĻ
    0.09
     Elm
    0.09
    大楼
    0.09
    æŁıæŀĹ
    0.09
    èĢģ人家
    0.09
    Activations Density 0.008%

    No Known Activations