© 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. 29904
    Prev
    Next
    INDEX
    Explanations

    components component

    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
     Available
    -0.08
    Available
    -0.07
     available
    -0.07
    iers
    -0.06
    对äºİè¿ĻäºĽ
    -0.06
    ç´ĭ
    -0.06
    .Safe
    -0.06
    schlag
    -0.06
    æ¡ĪçļĦ
    -0.06
    tracked
    -0.06
    POSITIVE LOGITS
     components
    0.09
     component
    0.08
     complementary
    0.08
    components
    0.08
     COMPONENT
    0.08
    inte
    0.08
     компоненÑĤÑĭ
    0.08
    -components
    0.07
     Components
    0.07
    лиз
    0.07
    Activations Density 0.008%

    No Known Activations