© 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. 29936
    Prev
    Next
    INDEX
    Explanations

    orientation and its related concepts

    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
    гÑĢан
    -0.08
    voud
    -0.08
    -orange
    -0.08
    aret
    -0.08
    féle
    -0.07
    nasium
    -0.07
    å¦ĤæѤä¸ĢæĿ¥
    -0.07
    ishly
    -0.07
    rd
    -0.07
    кÑĢаÑĤно
    -0.07
    POSITIVE LOGITS
    ally
    0.10
    ä¸įæĺİçļĦ
    0.09
    ebr
    0.08
    ients
    0.08
    achr
    0.08
    ศึà¸ģษา
    0.08
    OfFile
    0.08
    undas
    0.08
    åĴĮåĨħ容
    0.08
    oins
    0.08
    Activations Density 0.011%

    No Known Activations