© 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. 65442
    Prev
    Next
    INDEX
    Explanations

    size and scale measurements

    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
    åıĬéĶĢåĶ®
    -0.10
    ä¸ĩå¹´
    -0.09
     McGu
    -0.08
    GetData
    -0.08
     Ingr
    -0.08
    WithValue
    -0.08
    åŃ½
    -0.08
    Scores
    -0.08
    úi
    -0.08
    wäl
    -0.08
    POSITIVE LOGITS
    anz
    0.08
     size
    0.07
    大å°ıçļĦ
    0.07
     اÙĦØŃجÙħ
    0.06
    size
    0.06
    B
    0.06
    èµĦ
    0.06
    -size
    0.06
    -scale
    0.06
    èĢĮä¸Ķæĺ¯
    0.06
    Activations Density 0.677%

    No Known Activations