© 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. 26413
    Prev
    Next
    INDEX
    Explanations

    amine, tin, gas, ate

    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
     casual
    -0.07
    ç¾ģ
    -0.07
     zoom
    -0.07
    好好çļĦ
    -0.06
    çŃīåIJĦ项
    -0.06
    äºĨä¹Ī
    -0.06
    ä¸įçŁ¥éģĵèĩªå·±
    -0.06
    å¥½å¥½åľ°
    -0.06
    å°¸
    -0.06
    åĩĦåĩī
    -0.06
    POSITIVE LOGITS
     preferred
    0.10
     preferably
    0.10
    preferred
    0.10
     preferable
    0.09
    prefer
    0.09
    人æĪĸ
    0.09
     inexpensive
    0.09
    пÑĢом
    0.09
     readily
    0.09
     alternatives
    0.09
    Activations Density 0.144%

    No Known Activations