© 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. 35195
    Prev
    Next
    INDEX
    Explanations

    sap s/4 hana, ABAP class, condition expression

    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
    èļĬ
    -0.09
    è¢ĭ
    -0.09
    usher
    -0.09
    Ô½
    -0.09
    å®īåħ¨ä¿Ŀéļľ
    -0.09
    æ¯ıä½į
    -0.09
    inds
    -0.09
    =~
    -0.09
    æŁĦ
    -0.09
    åħ´æĹº
    -0.09
    POSITIVE LOGITS
    .sap
    0.10
    æ±¾
    0.09
     sap
    0.09
     SAP
    0.09
    sap
    0.09
    .po
    0.08
    plit
    0.08
    çijĻ
    0.08
    æİ¢
    0.08
    ç¨İåĬ¡å±Ģ
    0.08
    Activations Density 0.042%

    No Known Activations