© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6735
    Prev
    Next
    INDEX
    Explanations

    proper nouns and foreign 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
     Kemp
    -0.11
    ä¸Ĭå²Ĺ
    -0.08
    ams
    -0.08
    èIJ¥éĢłèī¯å¥½
    -0.08
    ãĥĻãĥ³
    -0.08
    社ä¼ļå®ŀè·µ
    -0.08
    æ´¹
    -0.08
    éĵ®
    -0.08
    Ì
    -0.08
    è¯ļæĦı
    -0.08
    POSITIVE LOGITS
    ellan
    0.11
    asto
    0.09
    osite
    0.09
    æİĴè¡Į
    0.09
    arged
    0.09
    çĶŁæ°Ķ
    0.09
     именно
    0.09
    IRON
    0.09
    ç¢ĵ
    0.09
    gro
    0.09
    Activations Density 0.288%

    No Known Activations