© 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. 57379
    Prev
    Next
    INDEX
    Explanations

    medium heat

    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
    个人æĪĸ
    -0.08
    водов
    -0.07
    éĩī
    -0.07
    æīįèĥ½å®ŀçİ°
    -0.07
    ä¹Łä¸įä¸Ģå®ļ
    -0.07
    åĪĽéĢłåĩº
    -0.07
    è¾Ħ
    -0.07
    omod
    -0.07
    _DETECT
    -0.07
    asters
    -0.06
    POSITIVE LOGITS
    dle
    0.07
    ForResource
    0.07
    etta
    0.07
    åĨį度
    0.07
    åĨį次
    0.07
    elsey
    0.06
    artial
    0.06
    æĬĬæīĢæľīçļĦ
    0.06
    asz
    0.06
    oger
    0.06
    Activations Density 0.023%

    No Known Activations