© 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. 2949
    Prev
    Next
    INDEX
    Explanations

    shared or together

    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
    uzu
    -0.07
    fx
    -0.06
    HU
    -0.06
    hof
    -0.06
    ibal
    -0.06
    对åħ¶è¿Ľè¡Į
    -0.06
    FU
    -0.06
    หà¸Ļู
    -0.06
    亲åĴĮ
    -0.06
    yle
    -0.06
    POSITIVE LOGITS
    åħ±åIJĮ
    0.28
    åħ±åIJĮçļĦ
    0.26
     shared
    0.25
    çļĦåħ±åIJĮ
    0.22
    åħ±äº«
    0.22
    shared
    0.22
    Shared
    0.21
     Ùħشتر
    0.21
     gemeinsamen
    0.21
     gemeinsame
    0.21
    Activations Density 0.322%

    No Known Activations