© 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. 8555
    Prev
    Next
    INDEX
    Explanations

    math notation includes parentheses

    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
    æ¿
    -0.06
    ä»İè¿Ļ个
    -0.06
    9
    -0.06
    ince
    -0.06
    ikian
    -0.06
    “
    -0.06
    ovin
    -0.05
    вид
    -0.05
    ().
    -0.05
    7
    -0.05
    POSITIVE LOGITS
    iphers
    0.09
    áīµ
    0.08
    bir
    0.08
    esses
    0.08
    ipher
    0.08
    EObject
    0.08
    éĺħè¯»æľ¬æĸĩ
    0.08
    åĽ¾çīĩæĿ¥æºIJäºİç½ij绾
    0.08
    bservice
    0.08
    "]=>
    0.08
    Activations Density 0.016%

    No Known Activations