© 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. 2428
    Prev
    Next
    INDEX
    Explanations

    Cyrillic word fragments

    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
    ï¸ı
    -0.09
    åĹª
    -0.08
    opus
    -0.08
    åĽłåľ°
    -0.08
    ä¸ĭ游
    -0.08
    pheres
    -0.07
    à¹Į
    -0.07
    pedia
    -0.07
    icons
    -0.07
    è¿ĺæľī
    -0.07
    POSITIVE LOGITS
    å¾Ĺå¾Ī
    0.12
    满äºĨ
    0.11
    ä¸įéĶĻçļĦ
    0.09
    çļĦ羣å®ŀ
    0.09
    è§Ħ磩
    0.09
    人æĿĥ
    0.09
    çģ¾åĮº
    0.09
    羣å®ŀ
    0.09
    å¾Ĺå¤ļ
    0.08
    æ´»ä¸ĭåİ»
    0.08
    Activations Density 0.184%

    No Known Activations