© 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. 19699
    Prev
    Next
    INDEX
    Explanations

    utf-8 encoding and programming keywords

    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
    çĦ¶åIJİéĢļè¿ĩ
    -0.07
    acle
    -0.07
    oso
    -0.07
    cho
    -0.07
    ocop
    -0.06
    ÐłÐĺ
    -0.06
    ijnen
    -0.06
    -view
    -0.06
    aphrag
    -0.06
    che
    -0.06
    POSITIVE LOGITS
    undo
    0.08
    ombs
    0.08
    ä¸ĵ家æĮĩåĩº
    0.07
    λιÏĥ
    0.07
    ecraft
    0.07
    åĤį
    0.07
    ÙĪرد
    0.07
    åĬĽçļĦ
    0.07
    _undo
    0.07
    Undo
    0.07
    Activations Density 0.147%

    No Known Activations