© 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. 8121
    Prev
    Next
    INDEX
    Explanations

    future intent or action

    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
    æľĢçĥŃ
    -0.07
    åĩłä¹İ
    -0.07
    为己
    -0.07
    æłı
    -0.07
    ÅĪ
    -0.06
    лдÑĭ
    -0.06
     as
    -0.06
    åĪĴ
    -0.06
    éĤ£éĩĮ
    -0.06
    sse
    -0.06
    POSITIVE LOGITS
    åĦĢ
    0.08
    rib
    0.08
    koh
    0.08
    lici
    0.08
    人åijĺ对
    0.08
    REW
    0.08
    åŃ¦ä¹łåŀĭ
    0.07
    社ä¼ļæ²»å®ī
    0.07
    ritis
    0.07
    dba
    0.07
    Activations Density 0.001%

    No Known Activations