© 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. 43109
    Prev
    Next
    INDEX
    Explanations

    square root symbol

    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
    Vision
    -0.08
     Vision
    -0.07
     carp
    -0.07
    åĽ´
    -0.07
    æĢĿæĺİ
    -0.06
    áĢĶáĢ¹
    -0.06
    åİĨ
    -0.06
    å¾Ĵ
    -0.06
    åĽ°æī°
    -0.06
    runde
    -0.06
    POSITIVE LOGITS
    .Factory
    0.08
    onis
    0.07
     Anex
    0.07
     nij
    0.07
    LEASE
    0.07
     acom
    0.07
    اÙĤØ©
    0.07
    åĪĩå®ŀåģļåĪ°
    0.07
    fach
    0.07
    ordin
    0.07
    Activations Density 0.001%

    No Known Activations