© 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. 42123
    Prev
    Next
    INDEX
    Explanations

    navigation and directions

    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
    ype
    -0.07
    åħĭ鼷
    -0.07
    ä¸ĭéĿ¢å°±
    -0.07
    ëĭ´
    -0.07
    BlockSize
    -0.07
    å®Ŀ座
    -0.07
    oplevel
    -0.07
    rita
    -0.07
    uyên
    -0.07
    attro
    -0.06
    POSITIVE LOGITS
    导èĪª
    0.16
     navigation
    0.15
     navig
    0.15
    æĸ¹ä½į
    0.14
     compass
    0.13
    æĮĩå¼ķ
    0.13
    navigation
    0.13
     GPS
    0.13
     Navigation
    0.12
     guides
    0.12
    Activations Density 0.184%

    No Known Activations