© 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. 39845
    Prev
    Next
    INDEX
    Explanations

    summary or shortening

    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
    orme
    -0.08
    å°ıåŃIJ
    -0.07
    åIJīå°Ķ
    -0.07
    okol
    -0.07
     sortable
    -0.07
    ordin
    -0.07
    _nullable
    -0.07
    azes
    -0.07
    ÙĪجب
    -0.07
    è®¤çľŁå¯¹å¾ħ
    -0.06
    POSITIVE LOGITS
     gist
    0.10
     ial
    0.08
    æĢĿè·¯
    0.07
     idea
    0.07
    大æĦı
    0.07
     Ú©ÙĦÛĮ
    0.07
    itur
    0.07
    缩çŁŃ
    0.06
     shortened
    0.06
    çļĦæĢĿè·¯
    0.06
    Activations Density 0.047%

    No Known Activations