© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42388
    Prev
    Next
    INDEX
    Explanations

    space telescope or observatory

    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
    æģ¢å¤įåĪ°
    -0.07
    碱
    -0.07
    undy
    -0.07
    azo
    -0.07
    Konz
    -0.06
    ä¹ĭæĢ¥
    -0.06
    inh
    -0.06
     nhượng
    -0.06
    æģ¢å¤į
    -0.06
     modifiers
    -0.06
    POSITIVE LOGITS
     orbits
    0.08
    æĶ¿åºľéĩĩè´Ń
    0.08
     flagship
    0.07
    vem
    0.07
     spacecraft
    0.07
    çŃī大åŀĭ
    0.07
    UNCH
    0.07
     dedicated
    0.07
    à¸Ńà¸ĩà¸Ħà¹Į
    0.07
    éĢĢå½¹
    0.07
    Activations Density 0.042%

    No Known Activations