© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42881
    Prev
    Next
    INDEX
    Explanations

    Alzheimer's, PPARs, training process, pyroptosis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çŃīåħ¶ä»ĸ
    -0.07
    haft
    -0.06
    çİīæłij
    -0.06
    èİ·èµł
    -0.06
    æ¯ķç«Ł
    -0.06
    åħ³äºİå¼Ģå±ķ
    -0.06
    akai
    -0.06
    erar
    -0.06
    åıĸçļĦ
    -0.06
    åĵĨ
    -0.06
    POSITIVE LOGITS
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.07
    ãĥ¼ãĤ«ãĥ¼
    0.07
    .AF
    0.07
    uldig
    0.07
    ahas
    0.07
    andan
    0.06
    imak
    0.06
    ëĭĪìĬ¤
    0.06
    аниÑĨ
    0.06
    .Body
    0.06
    Activations Density 0.010%

    No Known Activations