© 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. 30924
    Prev
    Next
    INDEX
    Explanations

    version number

    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
    amn
    -0.08
    麦åŃIJ
    -0.07
    érate
    -0.06
    uto
    -0.06
    ny
    -0.06
    缸åºĶ
    -0.06
    edy
    -0.06
    enc
    -0.06
     highs
    -0.06
    OCO
    -0.06
    POSITIVE LOGITS
     Dodat
    0.08
    ochond
    0.08
    atian
    0.08
     ReturnValue
    0.07
    .runner
    0.07
    éĢīè°ĥ
    0.07
    даниÑı
    0.07
    çļĦåĬŀæ³ķ
    0.07
    åĵĴ
    0.07
    ÙĪØ¡
    0.07
    Activations Density 0.003%

    No Known Activations