© 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. 65180
    Prev
    Next
    INDEX
    Explanations

    built based on

    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
    ctal
    -0.07
    æĿijéķĩ
    -0.07
    igmat
    -0.07
    ä¸įèĭŁ
    -0.07
     transitional
    -0.07
     Sche
    -0.07
    ק×Ļ
    -0.07
    æĪIJçĨŁ
    -0.07
     Fra
    -0.06
    IDX
    -0.06
    POSITIVE LOGITS
    以å¾ħ
    0.09
    以å¤ĩ
    0.07
    lop
    0.07
    оÑĤов
    0.07
    mist
    0.07
    æĹĹé¼ĵ
    0.07
    æĥ°
    0.06
    angk
    0.06
    ÑĥÑĩ
    0.06
    ä¸ĢæµģçļĦ
    0.06
    Activations Density 0.100%

    No Known Activations