© 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. 11490
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

    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
    EAR
    -0.07
    ä¸ĩæĪ·
    -0.07
    家åĸ»æĪ·
    -0.07
    ÑģпеÑĪ
    -0.07
    Tro
    -0.07
    elix
    -0.07
    åIJĪãģĦ
    -0.07
     overhaul
    -0.07
    åIJĦè¡Į
    -0.07
    .launch
    -0.07
    POSITIVE LOGITS
    åĪļæīį
    0.09
    âĭ®
    0.08
    ugin
    0.08
    oooooooo
    0.08
     полÑĥÑĩи
    0.08
    åįģ足
    0.08
    èĹ©
    0.08
    åĽºçĦ¶
    0.07
    éĿŀè¦ģ
    0.07
    æĥħ人
    0.07
    Activations Density 0.661%

    No Known Activations