© 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. 62250
    Prev
    Next
    INDEX
    Explanations

    Brexit campaign, gun control, animal rights, veterinary medicine, wildlife art, Yes campaign, fintech

    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
    è¡Įäºĭ
    -0.07
    pa
    -0.07
    fun
    -0.07
    abric
    -0.07
    人çĶŁ
    -0.07
    åĴĮè¦ģæ±Ĥ
    -0.06
    edList
    -0.06
    mi
    -0.06
    ç»ı
    -0.06
    çļĦäºĭ项
    -0.06
    POSITIVE LOGITS
    å·¥ä½ľå¼Ģå±ķ
    0.08
    æĹłæķ°çļĦ
    0.07
     pie
    0.07
    äche
    0.07
    isal
    0.07
    ä½ķå¿ħ
    0.07
    第ä¸Ģå±Ĭ
    0.07
    otland
    0.07
    aker
    0.07
    apor
    0.07
    Activations Density 0.029%

    No Known Activations