© 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. 38265
    Prev
    Next
    INDEX
    Explanations

    `.y` or `_out` followed by punctuation

    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
    xDA
    -0.08
    çĤİé»Ħ
    -0.07
    re
    -0.07
    .ids
    -0.07
    _resolver
    -0.07
    åĵģçīĮ形象
    -0.07
    èĦ¸åŀĭ
    -0.07
    å®ŀåIJį
    -0.07
    ()._
    -0.07
    åĩŃçĿĢ
    -0.07
    POSITIVE LOGITS
    çĴĢ
    0.08
    ä¸İç»´ä¿®
    0.07
    ilh
    0.07
    scanf
    0.07
    enschaft
    0.06
     nominate
    0.06
    æĽ²æ±Ł
    0.06
     ACM
    0.06
    åį°
    0.06
    aster
    0.06
    Activations Density 0.004%

    No Known Activations