© 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. 17006
    Prev
    Next
    INDEX
    Explanations

    defined as

    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
    ç´łè´¨æķĻèĤ²
    -0.07
    驼
    -0.07
    <|box_end|>
    -0.07
    kit
    -0.07
    amedi
    -0.07
    磶
    -0.07
    ussion
    -0.07
    ë¹ħ
    -0.07
    atable
    -0.06
    .VisualStudio
    -0.06
    POSITIVE LOGITS
    å®ļä¹ī为
    0.10
     defined
    0.08
     Defined
    0.08
    Defined
    0.08
    å®ļä¹ī
    0.08
    .ua
    0.07
    åĿİ
    0.07
    çļĦå®ļä¹ī
    0.07
    å®ļä¹īçļĦ
    0.07
    defined
    0.07
    Activations Density 0.009%

    No Known Activations