© 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. 47612
    Prev
    Next
    INDEX
    Explanations

    Starts with list words and continues

    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
    ught
    -0.07
    .tel
    -0.07
    ús
    -0.07
    tel
    -0.06
    qid
    -0.06
    ighb
    -0.06
     HQ
    -0.06
    ç¾Į
    -0.06
    å°ĨæĿ¥çļĦ
    -0.06
    evens
    -0.06
    POSITIVE LOGITS
     Ø£ÙĪÙĦاÙĭ
    0.08
    é¦ĸåħĪéľĢè¦ģ
    0.08
    é¦ĸåħĪ
    0.08
    먼
    0.08
    alisa
    0.07
    é¦ĸåħĪåľ¨
    0.07
     Primero
    0.07
    èĮĥæĸĩç½ij
    0.07
    çijľ
    0.07
    oad
    0.07
    Activations Density 0.160%

    No Known Activations