© 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. 50419
    Prev
    Next
    INDEX
    Explanations

    defines or characterizes

    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
    ä¸ĩ
    -0.08
    راÙģÛĮ
    -0.07
    Metrics
    -0.07
    pollo
    -0.07
    metrics
    -0.07
    _fmt
    -0.07
    éľĩæĥĬ
    -0.07
    οÏį
    -0.07
    åĪĢåŃIJ
    -0.07
    çľ¯çľ¯
    -0.06
    POSITIVE LOGITS
     context
    0.08
     Bref
    0.07
    éĻIJå®ļ
    0.07
    æī¿
    0.07
    nton
    0.06
     playground
    0.06
    æ³ĽæĮĩ
    0.06
    å·²ä¹ħ
    0.06
    代表æĢ§çļĦ
    0.06
    TY
    0.06
    Activations Density 0.380%

    No Known Activations