© 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. 38561
    Prev
    Next
    INDEX
    Explanations

    human pancreatic cancer

    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
    åIJijåĨħ
    -0.07
    è¿Ŀæ³ķè¡Į为
    -0.07
     Seger
    -0.07
    zii
    -0.07
    äºĮè¦ģ
    -0.07
    rs
    -0.07
    hiba
    -0.07
    çĤ¹èĩ³
    -0.06
    aise
    -0.06
    ms
    -0.06
    POSITIVE LOGITS
    飯
    0.07
     timeStamp
    0.07
    pecies
    0.07
    ksam
    0.07
    çIJª
    0.06
    åįķ个
    0.06
    Ø·ÙĬÙĨ
    0.06
    çłĶ
    0.06
    é©°
    0.06
     Oficial
    0.06
    Activations Density 0.001%

    No Known Activations