© 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. 33121
    Prev
    Next
    INDEX
    Explanations

    program file loading and configuration

    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
    Ľ
    -0.07
    ctors
    -0.06
    InstanceId
    -0.06
    KeyId
    -0.06
    ComputedStyle
    -0.06
    assar
    -0.06
    developers
    -0.06
    CTOR
    -0.06
    帷å¹ķ
    -0.06
    CustomerId
    -0.06
    POSITIVE LOGITS
    .Companion
    0.08
    .tem
    0.08
    .prototype
    0.08
    gev
    0.08
    .self
    0.07
     ripr
    0.07
    >::
    0.07
    ihak
    0.07
    notated
    0.07
    _MANY
    0.07
    Activations Density 0.560%

    No Known Activations