© 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. 8879
    Prev
    Next
    INDEX
    Explanations

    down, defense, defocusing

    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
    æŁĦ
    -0.07
    åIJīåĩ¶
    -0.07
    ili
    -0.07
     mur
    -0.06
    ixel
    -0.06
    -li
    -0.06
    rex
    -0.06
    ux
    -0.06
    åıĮ缮
    -0.06
    ä¸Ģ声
    -0.06
    POSITIVE LOGITS
    akis
    0.09
    naan
    0.08
    ä¸Ĭ大
    0.08
    VII
    0.08
    à¤ł
    0.08
    CIM
    0.08
    ancellationToken
    0.08
    IVI
    0.07
    warts
    0.07
    živ
    0.07
    Activations Density 0.342%

    No Known Activations