© 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. 58871
    Prev
    Next
    INDEX
    Explanations

    investigation and legal proceedings

    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
    çĻ»
    -0.11
    ç«ĭ马
    -0.10
    ä¾£
    -0.10
    ä¹°åįķ
    -0.10
    åħ»
    -0.10
    åıĺåİĭ
    -0.10
    赢家
    -0.09
    éĺĨ
    -0.09
    üz
    -0.09
    溢
    -0.09
    POSITIVE LOGITS
    æīĵåĩ»
    0.12
    Boston
    0.09
    åį·
    0.09
    æĬĵä½ı
    0.09
    èĬ¬
    0.09
    ä¸ĵ项æĸĹäºī
    0.09
    æ¡Ī件
    0.09
    çĬ¯ç½ª
    0.08
    åŁºåľ°
    0.08
    åĪijäºĭæ¡Ī件
    0.08
    Activations Density 0.084%

    No Known Activations