© 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. 11958
    Prev
    Next
    INDEX
    Explanations

    incoming or entering

    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
    ilat
    -0.07
    stitu
    -0.07
    èªĬ
    -0.07
    åĩºæĿ¥äºĨ
    -0.07
    åĩºä¾Ĩ
    -0.07
    excel
    -0.07
    nameof
    -0.07
    åįĬçĤ¹
    -0.07
    urer
    -0.07
     pou
    -0.07
    POSITIVE LOGITS
     inputs
    0.08
    à¹Ģà¸Ĥà¹īาà¹Ħà¸Ľ
    0.08
    inputs
    0.08
    å¼Ĺåħ°
    0.08
    _ACCEPT
    0.08
     fusion
    0.07
    Combo
    0.07
     incoming
    0.07
    è½°
    0.07
     entering
    0.07
    Activations Density 0.002%

    No Known Activations