© 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. 23010
    Prev
    Next
    INDEX
    Explanations

    the Philippines

    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
    æŁ¥çľĭçŃĶæ¡Ī
    -0.07
    ãĤ·ãĥ³
    -0.07
    ковод
    -0.06
    azi
    -0.06
    inden
    -0.06
    ingen
    -0.06
    æĹ¥è®°
    -0.06
     classy
    -0.06
    è¹²
    -0.06
    _SID
    -0.06
    POSITIVE LOGITS
    _ctxt
    0.08
     Dyn
    0.08
    udder
    0.08
    çŁ
    0.07
    alous
    0.07
    æī©å±ķèµĦæĸĻ
    0.07
    خاÙĨ
    0.07
     Следова
    0.07
    juta
    0.07
     embr
    0.07
    Activations Density 0.008%

    No Known Activations