© 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. 49262
    Prev
    Next
    INDEX
    Explanations

    specifications or notes

    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
    ึà¹Īà¸ĩ
    -0.07
     nim
    -0.07
    ode
    -0.07
    isata
    -0.07
    _SITE
    -0.07
    imeo
    -0.06
    çĪª
    -0.06
     Saul
    -0.06
    人åıĤ
    -0.06
    is
    -0.06
    POSITIVE LOGITS
    zÃŃ
    0.08
    ç»Ħåijĺ
    0.08
    ä¸ŃåŃĹ
    0.07
    achs
    0.07
    ouc
    0.07
    สà¸ģุล
    0.07
    çĿĽ
    0.07
    tern
    0.07
    жÑĮÑı
    0.07
    çľī
    0.07
    Activations Density 0.001%

    No Known Activations