© 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. 4211
    Prev
    Next
    INDEX
    Explanations

    Rich EXTERIOR

    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
    orti
    -0.09
    à¯įத
    -0.09
    оÑĩки
    -0.09
    ontro
    -0.08
    inni
    -0.08
    gy
    -0.08
    yec
    -0.08
    yssey
    -0.07
    izon
    -0.07
    stell
    -0.07
    POSITIVE LOGITS
    er
    0.07
    oref
    0.06
    èĮ¹
    0.06
    idel
    0.06
    otella
    0.06
    ¢
    0.06
    è²Į
    0.05
    este
    0.05
    ©
    0.05
     Rich
    0.05
    Activations Density 0.003%

    No Known Activations