© 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. 3109
    Prev
    Next
    INDEX
    Explanations

    then from this

    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
    arvi
    -0.09
    女éĥİ
    -0.08
    å¾Īå¤ļä¼ģä¸ļ
    -0.08
    æŶ髦
    -0.07
    opian
    -0.07
    abal
    -0.07
    ÙĬÙģÙĬØ©
    -0.07
    swick
    -0.07
    é¾Ļçİĭ
    -0.07
    好æĥ³
    -0.07
    POSITIVE LOGITS
     getApp
    0.07
    çĶ±æѤ
    0.07
    ãĤĮãģ°
    0.07
    å¾Ĺåĩº
    0.07
     conclu
    0.07
    ãģĻãĤĮãģ°
    0.07
    Finally
    0.07
    zell
    0.07
     appl
    0.07
     further
    0.06
    Activations Density 0.006%

    No Known Activations