© 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. 61293
    Prev
    Next
    INDEX
    Explanations

    treated

    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
    伸
    -0.07
     cyclic
    -0.07
    otin
    -0.07
    aben
    -0.07
     Ross
    -0.06
    aring
    -0.06
    ä¸Ģå¸Ĩ
    -0.06
    äºĮæĺ¯
    -0.06
    äºĮæĺ¯è¦ģ
    -0.06
    .removeListener
    -0.06
    POSITIVE LOGITS
    eira
    0.08
    å¾Ĺä½ı
    0.07
    åĤ»åĤ»
    0.07
     Hubb
    0.07
    orna
    0.07
    æłĩè¯Ń
    0.07
    ripper
    0.07
    åı¯æĥ³
    0.07
    Unt
    0.07
    ripe
    0.07
    Activations Density 0.437%

    No Known Activations