© 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. 65215
    Prev
    Next
    INDEX
    Explanations

    quantifier logic and calculus notation

    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
    ahan
    -0.07
    mal
    -0.06
    级
    -0.06
    [][
    -0.06
    ç²Ĵ
    -0.06
    ê¸ī
    -0.06
    çļĦéĩį
    -0.06
    åĬ²
    -0.06
    irmed
    -0.06
    efined
    -0.06
    POSITIVE LOGITS
    èĢĺ
    0.10
    åĴĮåįķä½į
    0.08
    åĴĮåĨħ容
    0.08
    åıĬ使çĶ¨
    0.08
    åħ®
    0.07
    vasti
    0.07
    åıĬéħįå¥Ĺ
    0.07
    ä½ı建
    0.07
    èĢĮè¨Ģ
    0.07
    reso
    0.07
    Activations Density 0.011%

    No Known Activations