© 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. 9725
    Prev
    Next
    INDEX
    Explanations

    controller-row, controller.m, actor

    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
    èīĩ
    -0.07
    iri
    -0.07
    缼ä¼ļ
    -0.06
    ire
    -0.06
    沧
    -0.06
    ijin
    -0.06
    士
    -0.06
    èĢ»
    -0.06
     lenses
    -0.06
     afg
    -0.06
    POSITIVE LOGITS
    AWN
    0.08
    åĨįä¹Ł
    0.08
    renom
    0.08
    esan
    0.07
    olet
    0.07
     neither
    0.07
    bish
    0.07
    éħİ
    0.07
     âĵĴ
    0.07
    -Disposition
    0.07
    Activations Density 0.097%

    No Known Activations