© 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. 32324
    Prev
    Next
    INDEX
    Explanations

    “quote” phrases

    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
    (Void
    -0.08
    奢
    -0.08
    otos
    -0.07
    ässe
    -0.07
    -validator
    -0.07
    ãn
    -0.07
    assage
    -0.07
    althy
    -0.07
    ostal
    -0.07
    åİŁåĪ¤
    -0.07
    POSITIVE LOGITS
    dq
    0.07
    DAQ
    0.06
    åĽ½ä¹ĭ
    0.06
     question
    0.06
    é£ĺé£ĺ
    0.06
    å±±ä¹ĭ
    0.06
    çļ®ä¹¦
    0.06
    cipe
    0.06
     questions
    0.06
    olland
    0.06
    Activations Density 0.061%

    No Known Activations