© 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. 63493
    Prev
    Next
    INDEX
    Explanations

    celestial bodies: sun, moon, stars

    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
    çĻ¾å®¶
    -0.08
     Jungle
    -0.07
    èįĨæ£ĺ
    -0.07
    å²ģæľĪ
    -0.07
    æĺ¥èī²
    -0.07
    æľīåij³
    -0.07
    æĺ¥åħī
    -0.07
    udit
    -0.07
    ä¸įéĢļ
    -0.06
     Wave
    -0.06
    POSITIVE LOGITS
    å¤ľç©º
    0.11
    天空
    0.10
    天空ä¸Ń
    0.10
    çħ§èĢĢ
    0.09
     skies
    0.09
     sky
    0.09
     celestial
    0.09
    äºijå±Ĥ
    0.09
    缴å°Ħ
    0.09
     اÙĦسÙħاء
    0.09
    Activations Density 0.065%

    No Known Activations