© 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. 10773
    Prev
    Next
    INDEX
    Explanations

    steps and processes

    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
    bacher
    -0.08
    žil
    -0.07
    æĪĺæĸĹåĬĽ
    -0.07
    å®ŀçĶ¨
    -0.07
    å®Ŀåīij
    -0.07
    PropertyValue
    -0.07
    одно
    -0.07
    çĶ·
    -0.07
     Jeu
    -0.07
    ANGED
    -0.07
    POSITIVE LOGITS
     gathering
    0.09
     먼ìłĢ
    0.09
    é¦ĸåħĪåľ¨
    0.08
    ä¹ĭåĪĿ
    0.08
    åĩĨå¤ĩ
    0.08
    éĢīå®ļ
    0.08
    éĢī好
    0.08
    é¦ĸåħĪè¦ģ
    0.08
    .prepare
    0.08
    å¤ĩ
    0.08
    Activations Density 0.172%

    No Known Activations