© 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. 27872
    Prev
    Next
    INDEX
    Explanations

    cyborg dragonflies

    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
    èijĨ
    -0.06
    å°Ĩæķ´ä¸ª
    -0.06
    oter
    -0.06
    éļĪ
    -0.06
    mise
    -0.06
    对æīĢ
    -0.06
    åı¬éĽĨ
    -0.05
    heber
    -0.05
    èĥŀèĥİ
    -0.05
    бал
    -0.05
    POSITIVE LOGITS
    araf
    0.08
    wir
    0.08
    éĩijä¸Ŀ
    0.08
    aisons
    0.08
    anst
    0.08
    ä¸Ńéĩij
    0.08
    reature
    0.08
    è¤ĩ
    0.07
    agli
    0.07
    ÑĨеп
    0.07
    Activations Density 0.001%

    No Known Activations