© 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. 22884
    Prev
    Next
    INDEX
    Explanations

    batting stats

    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
    æĹłäºĭ
    -0.07
    inci
    -0.07
     Giovan
    -0.07
    createUrl
    -0.06
    å¦Ĥåħ¶
    -0.06
    grav
    -0.06
    çĴ§
    -0.06
    à¸Īา
    -0.06
     Aires
    -0.06
    eko
    -0.06
    POSITIVE LOGITS
    ambang
    0.09
     compag
    0.08
    -holder
    0.07
    ạnh
    0.07
    å¹´æľĪ
    0.07
    evers
    0.07
    çļĦç¡®
    0.07
    resents
    0.07
    管çIJĨæīĢ
    0.07
    anness
    0.07
    Activations Density 0.070%

    No Known Activations