© 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. 8397
    Prev
    Next
    INDEX
    Explanations

    extraterrestrial, terrorist, philosophical, relations, face

    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
    ysin
    -0.08
    udi
    -0.07
    Ø®ÙĪا
    -0.07
    quote
    -0.07
     fru
    -0.07
    ç´³
    -0.07
    egna
    -0.07
     quarti
    -0.07
    UBLISH
    -0.07
    æŁ¥éĺħ
    -0.07
    POSITIVE LOGITS
    çļĦ人äºĭ
    0.06
    çļĦä¸Ģ项æĺ¯
    0.06
    å¿ľ
    0.06
    o
    0.06
    _runner
    0.06
    对人çļĦ
    0.06
    秦
    0.06
     Leib
    0.06
    æĦıä¹īä¸ĬçļĦ
    0.06
    åħĪ秦
    0.06
    Activations Density 0.079%

    No Known Activations