© 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. 39519
    Prev
    Next
    INDEX
    Explanations

    identifier, formulation, notebook

    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
    ilas
    -0.09
    æijĬ
    -0.07
    精彩åĨħ容
    -0.07
    ลาส
    -0.07
    ãĤ¢ãĤ«
    -0.07
    åħįè´¹åľ¨çº¿
    -0.07
    åķ¦
    -0.07
    PropertyValue
    -0.07
    atico
    -0.07
    razier
    -0.07
    POSITIVE LOGITS
    BuilderFactory
    0.10
    çļĦè§ĦåĪĻ
    0.10
    è§ĦåĪĻ
    0.10
     rules
    0.10
    è§Ħå®ļ
    0.10
    -types
    0.10
    è¦ıåīĩ
    0.09
    _rules
    0.09
     formula
    0.09
    types
    0.09
    Activations Density 0.801%

    No Known Activations