© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51808
    Prev
    Next
    INDEX
    Explanations

    used to or accustomed to

    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
    ÙĬÙĬÙĨ
    -0.09
    رÙĬÙĨ
    -0.09
    обÑĭ
    -0.09
    posal
    -0.08
    setup
    -0.08
    çł´åĿı
    -0.08
    åį±
    -0.08
    |RF
    -0.08
    èĩªæĿ¥
    -0.08
    åıĬåħ¶
    -0.08
    POSITIVE LOGITS
    åĻľ
    0.11
    è¿Ļä¸ĢçĤ¹
    0.09
    iliary
    0.09
    åĬŁè¯¾
    0.09
    åĴĮå®ĮåĸĦ
    0.09
    éĵ¡
    0.09
    ãģĤãģĴ
    0.09
     اÙĨÙĩ
    0.08
     disap
    0.08
    ionario
    0.08
    Activations Density 0.008%

    No Known Activations