© 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. 14409
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    åī²
    -0.07
    ä»İæĹł
    -0.07
    getLocation
    -0.07
    azzi
    -0.06
    çĻ¾ä¸ĩ
    -0.06
    缸ç»ĵåIJĪçļĦ
    -0.06
    à¸ģล
    -0.06
    Ïĥμ
    -0.06
    quil
    -0.06
    èĭĽ
    -0.06
    POSITIVE LOGITS
    ãģĿãĤĮãģ«
    0.08
    hofer
    0.07
    缴èĩ³
    0.07
    èĩªçĦ¶ä¹Ł
    0.07
    اش
    0.07
    ider
    0.07
    缴åĪ°
    0.07
    .follow
    0.07
    ä¾Ŀç¨Ģ
    0.07
    æݥ踵
    0.07
    Activations Density 0.007%

    No Known Activations