© 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. 64072
    Prev
    Next
    INDEX
    Explanations

    factory creation

    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
    acts
    -0.08
    aley
    -0.08
     processing
    -0.07
    act
    -0.07
    processing
    -0.07
    仲
    -0.07
    ToStr
    -0.06
     act
    -0.06
    _paint
    -0.06
    贯穿
    -0.06
    POSITIVE LOGITS
    åĪĽå»º
    0.12
    =create
    0.11
    newInstance
    0.11
    åĪĽå»ºçļĦ
    0.10
    çŃ¹å»º
    0.10
     constructors
    0.10
     létre
    0.10
     creation
    0.10
    create
    0.10
    /create
    0.10
    Activations Density 0.550%

    No Known Activations