© 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. 62418
    Prev
    Next
    INDEX
    Explanations

    non-English words and phrases

    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
    /or
    -0.10
    à¹Į
    -0.09
    assage
    -0.09
    reff
    -0.08
    ç§ĺ书
    -0.08
    æĸ·
    -0.08
    TRY
    -0.08
    温åĴĮ
    -0.08
    isor
    -0.08
    еÑģ
    -0.08
    POSITIVE LOGITS
    kah
    0.10
    ç©°
    0.10
    инÑĤеÑĢеÑģ
    0.09
    åĽ¡
    0.09
    æĴ©
    0.08
    å·²ä¹ħ
    0.08
     Touch
    0.08
     inj
    0.08
    è¦ģèĢĥèĻij
    0.08
    pliers
    0.08
    Activations Density 0.006%

    No Known Activations