© 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. 33141
    Prev
    Next
    INDEX
    Explanations

    ice age, geological epochs, paleoclimatic data

    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
    _section
    -0.07
    rz
    -0.06
    ç²¹
    -0.06
    à²ķà³įಷ
    -0.06
     fil
    -0.06
    è¶Ĭèµ°
    -0.06
     grat
    -0.06
    seh
    -0.06
    ä¸įç»ı
    -0.06
     vak
    -0.06
    POSITIVE LOGITS
    å½ĵæŶ
    0.12
    è·Ŀä»Ĭ
    0.11
     damals
    0.11
    åľ¨å½ĵæŶ
    0.10
    å½ĵæŶçļĦ
    0.10
    çķ¶æĻĤ
    0.10
     Paleo
    0.10
     damal
    0.09
     ancient
    0.09
    å®ľå±ħ
    0.09
    Activations Density 0.061%

    No Known Activations