© 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. 30946
    Prev
    Next
    INDEX
    Explanations

    contextual development, factors, variables, characteristics

    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
     division
    -0.08
    _regression
    -0.07
    :disable
    -0.07
    Division
    -0.07
     patro
    -0.07
    pati
    -0.06
     hạng
    -0.06
    egin
    -0.06
    abled
    -0.06
    .ff
    -0.06
    POSITIVE LOGITS
    /context
    0.18
     context
    0.17
    context
    0.16
     contexts
    0.15
     contextual
    0.14
    -context
    0.14
     Context
    0.14
     конÑĤек
    0.14
    à¹ģวà¸Ķลà¹īà¸Ńม
    0.13
     circumstances
    0.13
    Activations Density 0.062%

    No Known Activations