© 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. 38161
    Prev
    Next
    INDEX
    Explanations

    API access and factory creation

    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
     diam
    -0.07
     netr
    -0.07
     divisible
    -0.06
    éģ¥éģ¥
    -0.06
    Convertible
    -0.06
    æĿ¾
    -0.06
    osaur
    -0.06
     Viagra
    -0.06
    /WebAPI
    -0.06
    çĶ¨æĪ·çļĦéľĢæ±Ĥ
    -0.06
    POSITIVE LOGITS
    Factory
    0.11
    factory
    0.11
     Factory
    0.10
     factory
    0.10
    å®ŀä¾ĭ
    0.09
     instance
    0.09
    _factory
    0.09
    .factory
    0.08
    _instance
    0.08
    actory
    0.08
    Activations Density 0.588%

    No Known Activations