© 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. 14840
    Prev
    Next
    INDEX
    Explanations

    subject to be

    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
     iepazÄ«Å¡anÄģs
    -0.08
    æĸ°åĬłåĿ¡
    -0.08
    åīįèĢħ
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    Anywhere
    -0.08
    åľ¨è¿ĻäºĽ
    -0.08
    POSITE
    -0.08
    ROME
    -0.08
    istra
    -0.07
    imei
    -0.07
    POSITIVE LOGITS
     '
    0.07
    /
    0.07
    é¾Ļæ±Ł
    0.06
     ___
    0.06
     \"
    0.06
     E
    0.06
    驹
    0.06
     ('
    0.06
    âĢij
    0.06
     _____
    0.06
    Activations Density 0.630%

    No Known Activations