© 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. 47231
    Prev
    Next
    INDEX
    Explanations

    derivative calculation and tumor

    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
    Ľ
    -0.08
    /Register
    -0.08
    ecer
    -0.08
    åĪ°äºº
    -0.08
    èİ·å¾Ĺè¶ħè¿ĩ
    -0.08
    ı
    -0.08
    è¯´ä½ł
    -0.08
    ķĮ
    -0.07
    pname
    -0.07
    å·¥åķĨæĪ·
    -0.07
    POSITIVE LOGITS
    EZ
    0.06
    æĭĻ
    0.06
    .comment
    0.06
    umb
    0.06
     annotated
    0.06
    unds
    0.06
     Modifications
    0.06
    æģĻ
    0.06
    å¸ĥå°Ķ
    0.06
    rian
    0.06
    Activations Density 0.004%

    No Known Activations