© 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. 1902
    Prev
    Next
    INDEX
    Explanations

    high-level language

    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
    ifiable
    -0.09
    apé
    -0.09
    chnik
    -0.09
    edException
    -0.08
    bserv
    -0.08
    ebas
    -0.08
    次äºİ
    -0.08
    VICE
    -0.08
    ÏĨÏĮ
    -0.08
     iep
    -0.08
    POSITIVE LOGITS
    çĶ¨æĦı
    0.07
    most
    0.07
    ìľ¼
    0.07
    mente
    0.07
    aks
    0.07
    à·Ĵනà·Ĭ
    0.07
    ëį°ìļĶ
    0.07
    iu
    0.06
    راد
    0.06
    ly
    0.06
    Activations Density 0.002%

    No Known Activations