© 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. 43593
    Prev
    Next
    INDEX
    Explanations

    loss or access

    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
    uket
    -0.07
    év
    -0.07
    æ´»åĬ¨åľ°çĤ¹
    -0.06
    SCALL
    -0.06
    oms
    -0.06
     retom
    -0.06
     Blasio
    -0.06
    CallCheck
    -0.06
     Vinh
    -0.06
    TargetException
    -0.06
    POSITIVE LOGITS
    aurus
    0.07
    ä¸Ģè¾Ī
    0.07
    åįİ缼
    0.07
    akes
    0.07
    agger
    0.07
    tik
    0.07
    ake
    0.07
    æĨĶ
    0.07
    åĩłæĹ¥
    0.07
    reck
    0.06
    Activations Density 0.102%

    No Known Activations