© 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. 56879
    Prev
    Next
    INDEX
    Explanations

    assess whether, presence of, failure of

    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
    ormsg
    -0.09
    Anywhere
    -0.09
    StackTrace
    -0.08
    berra
    -0.08
    dash
    -0.08
     поÑĤÑĢебо
    -0.08
    ussin
    -0.08
    ActionCode
    -0.08
    erop
    -0.08
    éħ
    -0.08
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.10
     rather
    0.10
     *
    0.10
    èĢĮéĿŀ
    0.09
    çī¹å®ļ
    0.07
     chứ
    0.07
    æķ´ä¸ªäºº
    0.07
    rather
    0.07
    èĢĮå·²
    0.07
     Rather
    0.07
    Activations Density 0.114%

    No Known Activations