© 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. 51768
    Prev
    Next
    INDEX
    Explanations

    actions like upload, print, send, select

    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
    çĩ
    -0.07
    ़
    -0.06
    wohl
    -0.06
    æĢ§éĹ®é¢ĺ
    -0.06
    سة
    -0.06
    ²
    -0.06
    åĪĨ许
    -0.06
    بÙĪد
    -0.06
    çĶ«
    -0.06
     browsers
    -0.06
    POSITIVE LOGITS
    /upload
    0.08
    /delete
    0.08
    æĹłæĢ¨æĹłæĤĶ
    0.08
     ulang
    0.08
    Anything
    0.08
    åĴĮç»´æĬ¤
    0.08
    åĴĮçĽijçĿ£
    0.08
    /write
    0.08
     anything
    0.08
    /update
    0.08
    Activations Density 0.129%

    No Known Activations