© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14050
    Prev
    Next
    INDEX
    Explanations

    NOP sequences

    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
    èĭ¥æĺ¯
    -0.08
    è¦ģæĺ¯
    -0.07
     trivial
    -0.06
    ando
    -0.06
    quo
    -0.06
     dato
    -0.06
    å¤ļå¤ļå°ij
    -0.06
     Heal
    -0.06
    IfNeeded
    -0.06
    å·¦ä¸Ĭ
    -0.06
    POSITIVE LOGITS
    abase
    0.08
    ÑĦÑĢи
    0.08
    boli
    0.08
    rapy
    0.08
    aghan
    0.07
    rax
    0.07
    uko
    0.07
    糸
    0.07
    ÙĩراÙĨ
    0.07
    asilan
    0.07
    Activations Density 0.007%

    No Known Activations