© 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. 29866
    Prev
    Next
    INDEX
    Explanations

    global brands and services

    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
    为ä¸Ńå¿ĥçļĦ
    -0.06
     somewhat
    -0.06
    /software
    -0.05
     Tanner
    -0.05
    ../../
    -0.05
    éľĩ
    -0.05
    /
    -0.05
    åĢº
    -0.05
    åīįæľŁ
    -0.05
    åĮĸ
    -0.05
    POSITIVE LOGITS
    ®,
    0.12
    lobal
    0.12
     global
    0.10
    çļĦåħ¨çIJĥ
    0.10
    global
    0.10
    åħ¨çIJĥ
    0.10
     weltweit
    0.09
    .global
    0.09
    _errno
    0.09
    alsy
    0.09
    Activations Density 0.718%

    No Known Activations