© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48784
    Prev
    Next
    INDEX
    Explanations

    admin interfaces (GUI, Commander, Admin)

    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
    /facebook
    -0.07
    nia
    -0.06
    ensa
    -0.06
    ק×ķת
    -0.06
    /npm
    -0.06
     household
    -0.06
    è¹Ń
    -0.06
    ä¸įéķ¿
    -0.06
    çĪĨ竹
    -0.06
     artificial
    -0.06
    POSITIVE LOGITS
    ui
    0.09
    åĦĢ
    0.09
    view
    0.09
    çķĮéĿ¢
    0.09
     view
    0.09
    缴è§ĤçļĦ
    0.09
    agrid
    0.09
    æīĢè§ģ
    0.08
    -view
    0.08
    缴è§Ĥ
    0.08
    Activations Density 1.094%

    No Known Activations