© 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. 42765
    Prev
    Next
    INDEX
    Explanations

    current value or position

    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
    ides
    -0.08
    otrop
    -0.08
    ãģ©ãĤĤ
    -0.08
    idable
    -0.08
    åIJİéģĹçĹĩ
    -0.07
    ÙĪÚº
    -0.07
    å°½æľī
    -0.07
    à¹Ħà¸Ĺย
    -0.07
    codes
    -0.07
    /english
    -0.07
    POSITIVE LOGITS
    ledge
    0.11
    é¢Į
    0.08
    åıĬ以ä¸ĭ
    0.07
    bie
    0.07
    OrCreate
    0.07
    OrDefault
    0.07
     mức
    0.07
    åĴĮæľªæĿ¥
    0.07
    orary
    0.06
    (Current
    0.06
    Activations Density 0.038%

    No Known Activations