© 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. 9382
    Prev
    Next
    INDEX
    Explanations

    differential equations

    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
     Formula
    -0.09
    izen
    -0.09
    åı°ä¸Ĭ
    -0.09
    è´¢åĬĽ
    -0.08
    Formula
    -0.08
    éĺ¶å±Ĥ
    -0.08
    aroo
    -0.08
    ãĥ¥ãĥ¼
    -0.08
    kte
    -0.08
     оÑĦоÑĢм
    -0.08
    POSITIVE LOGITS
     equations
    0.11
    æĪĸå¤ļ
    0.10
    æĹħé¦Ĩ
    0.10
    çªĺ
    0.10
    æĸ¹
    0.10
    çĽ¥
    0.09
    æĻ¨æĬ¥
    0.09
    ä¸īæĿ¡
    0.09
     equation
    0.09
    systems
    0.09
    Activations Density 0.314%

    No Known Activations