© 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. 12458
    Prev
    Next
    INDEX
    Explanations

    geographic or organizational units

    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
    =User
    -0.08
    ä¹ĭä¸ĢçļĦ
    -0.08
    escu
    -0.08
    tera
    -0.08
    UGE
    -0.08
    бÑĥ
    -0.08
    emiz
    -0.08
    obao
    -0.07
    ouro
    -0.07
    åħ¶ä»ĸåĽ½å®¶
    -0.07
    POSITIVE LOGITS
     belonging
    0.09
     individuales
    0.07
     individually
    0.07
    sworth
    0.06
    æł¹æį®åħ¶
    0.06
    个ä½ĵ
    0.06
     individuais
    0.06
     randomly
    0.06
    ID
    0.06
     individual
    0.06
    Activations Density 0.405%

    No Known Activations