© 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. 22084
    Prev
    Next
    INDEX
    Explanations

    crossOrigin

    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
     ofApp
    -0.08
    ĮĢ
    -0.08
    udson
    -0.08
    æĥħç»ĵ
    -0.08
    ither
    -0.07
    lyn
    -0.07
    ossid
    -0.07
    åĢ¶
    -0.07
     rẽ
    -0.07
    tsx
    -0.07
    POSITIVE LOGITS
    cach
    0.06
    士æŀĹ
    0.06
    alang
    0.06
    inata
    0.05
    ublisher
    0.05
    erver
    0.05
    ãģ°
    0.05
    #error
    0.05
    обÑĢа
    0.05
     kang
    0.05
    Activations Density 1.832%

    No Known Activations