© 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. 41084
    Prev
    Next
    INDEX
    Explanations

    difference, error, change

    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
     Somm
    -0.07
     Maire
    -0.06
     Pren
    -0.06
    roadcast
    -0.06
    à¸Ĺร
    -0.06
    æŀģé«ĺ
    -0.06
     primitives
    -0.06
    leben
    -0.06
    _DECL
    -0.06
     lifes
    -0.06
    POSITIVE LOGITS
     deviation
    0.15
    åģı离
    0.14
    åģıå·®
    0.14
     deviations
    0.14
    å·®é¢Ŀ
    0.11
    è¶ħé¢Ŀ
    0.11
     excess
    0.11
     difference
    0.11
     deficit
    0.11
    ãģļãĤĮ
    0.10
    Activations Density 0.083%

    No Known Activations