© 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. 33367
    Prev
    Next
    INDEX
    Explanations

    lamp or lighting related devices

    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
    åį¦
    -0.07
    èħ¹åľ°
    -0.07
    é¾ĻèĻİ
    -0.07
    /from
    -0.07
     Roche
    -0.07
    ç¸
    -0.06
    ilhas
    -0.06
    templates
    -0.06
    waÅĤ
    -0.06
    çĬ¯çļĦ
    -0.06
    POSITIVE LOGITS
     bulbs
    0.13
     bulb
    0.13
    çģ¯
    0.13
    çģ¯åħ·
    0.13
    çģ¯æ³¡
    0.12
    çħ§æĺİ
    0.12
    ä¸ĢçĽı
    0.12
    çĨĦçģŃ
    0.12
    çĽı
    0.12
     lights
    0.11
    Activations Density 0.083%

    No Known Activations