© 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. 8313
    Prev
    Next
    INDEX
    Explanations

    simplifying calculations

    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
     everlasting
    -0.08
    ä»Ģ
    -0.07
     encoding
    -0.07
    ç¼ĸçłģ
    -0.07
    encode
    -0.07
    iern
    -0.07
    encoding
    -0.07
    schlag
    -0.07
    Ø·
    -0.07
     encode
    -0.07
    POSITIVE LOGITS
     tamp
    0.08
    äºĮ级
    0.08
     autof
    0.08
     اÙģت
    0.08
    ä½¼
    0.07
    èĩªå¼º
    0.07
    çĮ
    0.07
    æIJħ
    0.07
    åĴĮäºĮ
    0.07
    .subscription
    0.07
    Activations Density 0.001%

    No Known Activations