© 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. 35164
    Prev
    Next
    INDEX
    Explanations

    place names, company names, and technical terms

    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
    кÑĥп
    -0.09
     cú
    -0.09
    é¢ĩ
    -0.09
    avian
    -0.09
    mitt
    -0.09
    åİĺ
    -0.08
    вл
    -0.08
    éķĢ
    -0.08
    çĮľæµĭ
    -0.08
    оÑĦ
    -0.08
    POSITIVE LOGITS
    滹
    0.10
    ä¸Ģ次æĢ§
    0.09
    家åĸ»æĪ·æĻĵ
    0.09
     Rosenstein
    0.08
    æŃ»åİ»
    0.08
    ural
    0.08
    综åIJĪæ²»çIJĨ
    0.08
    ç¢į
    0.08
    çªĪ
    0.08
    ug
    0.08
    Activations Density 0.006%

    No Known Activations