© 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. 31241
    Prev
    Next
    INDEX
    Explanations

    is the second

    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
    ebel
    -0.08
     поÑĤе
    -0.08
    ÐļТ
    -0.08
    åĴ¨è¯¢çĥŃ线
    -0.08
    å±±æ¹ĸ
    -0.08
    emma
    -0.08
    iÃŁ
    -0.08
    æĸ°æĹ¶ä»£ä¸ŃåĽ½çī¹èī²ç¤¾ä¼ļ主ä¹ī
    -0.08
    etable
    -0.08
    à®±à¯įப
    -0.08
    POSITIVE LOGITS
    0.07
     Back
    0.06
     back
    0.06
    åĬĽè¡Į
    0.06
    Back
    0.06
    g
    0.06
     .
    0.06
    _back
    0.06
    å¡Į
    0.06
    æł¼æł¼
    0.06
    Activations Density 0.373%

    No Known Activations