© 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. 25540
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

    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
    ä¸į离
    -0.07
    èijĨ
    -0.07
    åĩĨ
    -0.07
     olmayan
    -0.07
    ($)
    -0.07
    äºĨçļĦ
    -0.07
     olev
    -0.07
    aul
    -0.07
    åĩłç§ĴéĴŁ
    -0.07
    ord
    -0.06
    POSITIVE LOGITS
    åĴĮçĻ½
    0.07
     ë¹Ħ롯íķľ
    0.07
    ç§ģæľį
    0.07
     jumlahnya
    0.06
     PROVIDED
    0.06
    åħ¶ä¸ī
    0.06
    upyter
    0.06
    imers
    0.06
    西æ¹ĸ
    0.06
     ÑĪÑĤÑĥк
    0.06
    Activations Density 0.123%

    No Known Activations