© 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. 9321
    Prev
    Next
    INDEX
    Explanations

    routes pathways

    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
    ¾
    -0.09
    ayo
    -0.07
    家åįıä¼ļ
    -0.07
    istrate
    -0.07
    trak
    -0.07
    аÑĪ
    -0.07
    heden
    -0.07
    otin
    -0.06
    egers
    -0.06
    body
    -0.06
    POSITIVE LOGITS
    inely
    0.10
    å¾ij
    0.10
    åĴĮæĸ¹æ³ķ
    0.09
    sweise
    0.09
    ä¸įçķħ
    0.09
    ologies
    0.09
    WAYS
    0.09
    éĢĶå¾Ħ
    0.09
    ential
    0.08
    ä¸įæĺİçļĦ
    0.08
    Activations Density 0.033%

    No Known Activations