© 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. 58765
    Prev
    Next
    INDEX
    Explanations

    Microsoft Visual Studio Solution File

    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
    åĭĩå¾Ģ缴åīį
    -0.09
    oves
    -0.07
    è¿ĺä¸įå¦Ĥ
    -0.07
    ä¸įå¦Ĥ
    -0.07
    èĬ³åįİ
    -0.07
    ä¸įåı¯æĢĿè®®
    -0.07
    á
    -0.07
     Mok
    -0.06
    loch
    -0.06
    å°Ķ
    -0.06
    POSITIVE LOGITS
    å±±ä¹ĭ
    0.09
     aupr
    0.08
    zinha
    0.07
    äºĭä¸Ń
    0.07
    æĪ²
    0.07
    inu
    0.07
    uxtap
    0.07
    urre
    0.07
    ISIBLE
    0.07
    -toast
    0.07
    Activations Density 0.001%

    No Known Activations