© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29970
    Prev
    Next
    INDEX
    Explanations

    amounts and increments

    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
    assem
    -0.08
    å°ĶåŁº
    -0.08
    æ³ķç½ij
    -0.08
    ãĥ©ãĥ«
    -0.08
    æĬ½æŁ¥æ£ĢæŁ¥
    -0.07
    ordio
    -0.07
    apura
    -0.07
    даÑĤ
    -0.07
     ulteri
    -0.07
    usas
    -0.07
    POSITIVE LOGITS
    æīĢå¼ķèµ·çļĦ
    0.10
    æ±½
    0.08
    ÎĶ
    0.08
    åıijçĶŁåľ¨
    0.08
    å¹ħ度
    0.08
    å¼ķèµ·çļĦ
    0.07
     increments
    0.07
    ä¸įå°ı
    0.07
     magnitude
    0.07
    轻微çļĦ
    0.07
    Activations Density 0.072%

    No Known Activations