© 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. 13279
    Prev
    Next
    INDEX
    Explanations

    setting to a value

    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
     lắm
    -0.07
    åĩºäºĨä¸Ģ
    -0.07
    .TryParse
    -0.07
    ç«ĭãģ¦
    -0.07
    åĩºæĿ¥äºĨ
    -0.07
    åĺĮ
    -0.07
    cci
    -0.07
    agit
    -0.07
    -assets
    -0.07
    åĩºäºĨä¸Ģ个
    -0.07
    POSITIVE LOGITS
     value
    0.07
    æĶ¹æĪIJ
    0.07
    æľīä½Ļ
    0.07
    æĶ¹ä¸º
    0.06
     whatever
    0.06
     newValue
    0.06
    好åIJİ
    0.06
     values
    0.06
     whichever
    0.06
    esz
    0.06
    Activations Density 0.084%

    No Known Activations