© 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. 61792
    Prev
    Next
    INDEX
    Explanations

    live. thanks

    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
    aring
    -0.08
    toa
    -0.07
    ieder
    -0.07
    ëm
    -0.07
    ey
    -0.07
    èįIJ
    -0.07
    umor
    -0.07
    ypress
    -0.07
    è¦ģä¸įè¦ģ
    -0.07
    ickle
    -0.07
    POSITIVE LOGITS
    éĿŀ常æĦŁè°¢
    0.08
    åĿļæĮģ
    0.07
    è¡Įæĸĩ
    0.07
    ä¸įçĶĺå¿ĥ
    0.07
     thanks
    0.06
    awa
    0.06
    å¿ħé¡»åĿļæĮģ
    0.06
    endir
    0.06
    çļĦä¸Ģ款
    0.06
    .persist
    0.06
    Activations Density 0.044%

    No Known Activations