© 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. 28071
    Prev
    Next
    INDEX
    Explanations

    celebrating holidays, machines, topic, walls, systems, hydro, telling

    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
     preca
    -0.08
    ç¢Į
    -0.07
    example
    -0.07
    æĿŀ
    -0.07
     invalid
    -0.07
     pewno
    -0.07
    åıįèĢĮä¼ļ
    -0.07
    åıįèĢĮ
    -0.07
    due
    -0.07
    iki
    -0.07
    POSITIVE LOGITS
    —who
    0.07
    ä¹ĭ以
    0.07
    —from
    0.07
    HasBeen
    0.07
    —that
    0.07
     Harness
    0.07
     juxtap
    0.07
    —
    0.07
     harness
    0.07
    èĪ¶
    0.07
    Activations Density 0.003%

    No Known Activations