© 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. 55519
    Prev
    Next
    INDEX
    Explanations

    acceleration to planets

    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
     sequ
    -0.06
    zam
    -0.06
    Duplicates
    -0.06
    æĶ¹éĿ©åĪĽæĸ°
    -0.06
    çĶŁåij½
    -0.06
    mer
    -0.06
    orti
    -0.06
    çĥŃçĥĪ
    -0.06
     thirsty
    -0.06
    å¼ŁåŃIJ
    -0.06
    POSITIVE LOGITS
    ä¸Ńå°ıåŀĭ
    0.08
    اص
    0.08
    Äħż
    0.08
     Schweizer
    0.08
    æľ¨æĺŁ
    0.07
    _minor
    0.07
    ä½į移
    0.07
    äºij天
    0.07
    allocation
    0.07
    ç«¥å¿ĥ
    0.07
    Activations Density 0.001%

    No Known Activations