© 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. 46376
    Prev
    Next
    INDEX
    Explanations

    git version, high, perimeter, _password

    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¬
    -0.07
    æī
    -0.07
    åĪ°è´¦
    -0.07
     sec
    -0.07
    uart
    -0.07
    right
    -0.07
    гина
    -0.06
    ibu
    -0.06
    ole
    -0.06
     ~>
    -0.06
    POSITIVE LOGITS
     hale
    0.07
    illard
    0.07
    å¾ħ
    0.07
     envol
    0.07
     exposure
    0.07
    çīĪæĿĥä¸İåħį责声æĺİ
    0.07
     simply
    0.07
    ront
    0.07
    _sink
    0.07
    ×ķר×Ļ
    0.07
    Activations Density 0.014%

    No Known Activations