© 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. 16613
    Prev
    Next
    INDEX
    Explanations

    subject to, based on

    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
    дне
    -0.08
    ä¹ĥèĩ³
    -0.07
    dj
    -0.07
    å¾ĭå·±
    -0.07
    nk
    -0.07
    UTE
    -0.07
    nement
    -0.07
    ÛķÚ©
    -0.07
    å¤ļç§įå½¢å¼ı
    -0.07
    éī´äºİ
    -0.07
    POSITIVE LOGITS
    ervis
    0.08
    äºİä¸Ģ
    0.07
    äºİ
    0.07
     to
    0.07
     of
    0.07
    orch
    0.07
    åŃĶ
    0.06
    ä¹İ
    0.06
    iring
    0.06
    ://
    0.06
    Activations Density 1.603%

    No Known Activations