© 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. 25768
    Prev
    Next
    INDEX
    Explanations

    citations e.g. `[@B1`

    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
    cliffe
    -0.08
    edale
    -0.08
    _lineno
    -0.08
    edList
    -0.08
     Programm
    -0.07
    SSIP
    -0.07
    croft
    -0.07
    สล
    -0.07
    misc
    -0.07
    ilding
    -0.07
    POSITIVE LOGITS
    为人
    0.07
     “
    0.06
    ä¸ĢæĹ¥
    0.06
    è¿Ļ
    0.06
    ansen
    0.06
    è¥
    0.06
    æĬij
    0.06
    çĨŁ
    0.06
     Lar
    0.06
    æĢ»
    0.06
    Activations Density 0.138%

    No Known Activations