© 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. 18480
    Prev
    Next
    INDEX
    Explanations

    UK, Norway, Draw

    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»Ģä¹ĪéĹ®é¢ĺ
    -0.07
    atel
    -0.07
    ffects
    -0.06
    lott
    -0.06
    ott
    -0.06
     characteristic
    -0.06
    bs
    -0.06
    atin
    -0.06
    "crypto
    -0.06
    æ¯Ķäºŀ
    -0.06
    POSITIVE LOGITS
    ä¸įæĹ©
    0.08
    ardia
    0.08
    elay
    0.08
    ä¸įæĶ¶
    0.07
    anzo
    0.07
     intending
    0.07
    大件
    0.07
    vidia
    0.07
    ä¸įçŁ¥éģĵä½ł
    0.07
    äh
    0.07
    Activations Density 0.008%

    No Known Activations