© 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. 64311
    Prev
    Next
    INDEX
    Explanations

    ph

    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
    èIJ½å®ŀæĥħåĨµ
    -0.08
    erot
    -0.08
    éĻµ
    -0.08
    ]}"
    -0.07
    =?",
    -0.07
    iaan
    -0.07
    åĪ°å¦Ĥä»Ĭ
    -0.07
    iel
    -0.07
    .FILES
    -0.07
     anonyme
    -0.07
    POSITIVE LOGITS
    iff
    0.07
     Fun
    0.07
    adem
    0.07
    ÏħÏĩ
    0.07
    trs
    0.06
    ringer
    0.06
    iosk
    0.06
     दरà¥į
    0.06
    à§įবর
    0.06
    -inf
    0.06
    Activations Density 0.024%

    No Known Activations