© 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. 30007
    Prev
    Next
    INDEX
    Explanations

    bicarbonate buffering

    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
    è±
    -0.07
    horse
    -0.07
     imm
    -0.07
    è°ĥçłĶåijĺ
    -0.07
     haut
    -0.06
    å¤ļå¾Ĺ
    -0.06
     Underground
    -0.06
    ãĤ¿ãĥ¼
    -0.06
    ZER
    -0.06
    ä¸Ģè·³
    -0.06
    POSITIVE LOGITS
     prevision
    0.08
    éĺ¿å§¨
    0.07
    TextNode
    0.07
    ighter
    0.07
    opper
    0.07
    Ø°Ùİا
    0.07
    oria
    0.07
    ailed
    0.07
    abee
    0.07
    enheim
    0.07
    Activations Density 0.004%

    No Known Activations