© 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. 8794
    Prev
    Next
    INDEX
    Explanations

    Daily Foto Introduction

    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
    éľĨ
    -0.09
    inox
    -0.08
    imed
    -0.08
     fir
    -0.08
    èĩªè¾¾
    -0.08
    iad
    -0.07
    .fm
    -0.07
    غÙĬ
    -0.07
    ÑĦей
    -0.07
    iac
    -0.07
    POSITIVE LOGITS
     Strut
    0.07
    解éĶģ
    0.07
     Shack
    0.07
    çī¢
    0.06
    ä¿Ħ
    0.06
    ÑĽ
    0.06
    omencl
    0.06
    æ§Ľ
    0.06
    çĶ¨éĴ±
    0.06
     Cash
    0.06
    Activations Density 0.001%

    No Known Activations