© 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. 2982
    Prev
    Next
    INDEX
    Explanations

    deterministic and predictable outcomes

    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
    اء
    -0.08
    IDEO
    -0.08
    enschutz
    -0.08
    à¹Ģà¸ŀิà¹Īà¸ĩ
    -0.08
    ạ
    -0.07
    ersen
    -0.07
     sụt
    -0.07
    itek
    -0.07
     kand
    -0.07
    微信æī«ä¸Ģæī«
    -0.07
    POSITIVE LOGITS
     deterministic
    0.11
     predict
    0.10
     prediction
    0.10
     predictable
    0.09
    é¢Ħæµĭ
    0.09
     Predict
    0.09
    predict
    0.08
     Prediction
    0.08
    Everything
    0.08
     Everything
    0.08
    Activations Density 0.017%

    No Known Activations