© 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. 58650
    Prev
    Next
    INDEX
    Explanations

    Fourth Court, izon targets

    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
    bard
    -0.07
     deposit
    -0.07
    ENN
    -0.07
     profil
    -0.07
    å½ĵåīįä½įç½®
    -0.07
    å¨ĩ妻
    -0.07
    Magnitude
    -0.06
     Profil
    -0.06
    otron
    -0.06
    ppen
    -0.06
    POSITIVE LOGITS
     تعداد
    0.10
     Anzahl
    0.09
     Connectivity
    0.09
    å¥ĩ
    0.09
     connectivity
    0.09
    æĢ»æķ°
    0.08
    线索æķ°éĩı
    0.08
    _Count
    0.08
    ushman
    0.08
     ÙĪعدد
    0.08
    Activations Density 0.008%

    No Known Activations