© 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. 55959
    Prev
    Next
    INDEX
    Explanations

    Burton, Toro, Tozer

    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
    ย
    -0.10
    çį¾
    -0.09
    бав
    -0.09
    ç¼ĥ
    -0.09
    èľ®
    -0.09
    é¢Ĭ
    -0.08
    æıĦ
    -0.08
    ingly
    -0.08
    ãģĦãģĨ
    -0.08
    IFF
    -0.08
    POSITIVE LOGITS
    å¼ĢæĿ¥
    0.11
    ç½¢
    0.09
     Loud
    0.09
    ally
    0.08
     ÑģÑĢеди
    0.08
     далек
    0.08
    è¡Įãģį
    0.08
    roid
    0.08
     enumerable
    0.08
    ãĢħ
    0.08
    Activations Density 0.001%

    No Known Activations