© 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. 18175
    Prev
    Next
    INDEX
    Explanations

    programming constructs and medical procedures

    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
    aeda
    -0.08
    quirer
    -0.07
    éĻ¤å¤ĸ
    -0.07
    纵çĦ¶
    -0.07
    个人页
    -0.07
    à¹Ħ
    -0.07
    è¶Ĭç§Ģ
    -0.07
     sogn
    -0.07
    learn
    -0.07
    TestId
    -0.07
    POSITIVE LOGITS
    اء
    0.07
    pren
    0.07
    inkan
    0.07
    åłª
    0.07
    dos
    0.07
    ãģĤãģ£ãģ¦
    0.07
    isos
    0.06
    zan
    0.06
     &)
    0.06
    proved
    0.06
    Activations Density 0.001%

    No Known Activations