© 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. 57197
    Prev
    Next
    INDEX
    Explanations

    joint capsule, etiology, feeling great

    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
    lex
    -0.08
    åIJ«ç¬ij
    -0.07
    èŤ
    -0.07
    еÑĤка
    -0.07
    ingles
    -0.06
    ä½łåĪ°åºķ
    -0.06
     reverse
    -0.06
    ä¹³
    -0.06
    ä¸įå®ĮçļĦ
    -0.06
    Reverse
    -0.06
    POSITIVE LOGITS
    Âł
    0.11
    elmi
    0.08
     Âł Âł
    0.08
     Âł Âł Âł Âł
    0.08
    0.08
    ³³
    0.08
     Âł
    0.07
    bjerg
    0.07
    KOM
    0.07
    糸
    0.07
    Activations Density 0.127%

    No Known Activations