© 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. 18478
    Prev
    Next
    INDEX
    Explanations

    specified or determined

    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
    ANH
    -0.08
    imai
    -0.08
    èĴĻå¾·
    -0.08
    alles
    -0.08
     QApplication
    -0.07
    éĶIJæĦıè¿Ľåıĸ
    -0.07
    akaan
    -0.07
    åıĬæĹ¶è§£åĨ³
    -0.07
    uria
    -0.07
    ải
    -0.07
    POSITIVE LOGITS
    วà¹Īาà¹Ģà¸Ľà¹ĩà¸Ļ
    0.06
    ä½ľä¸º
    0.06
     sebagai
    0.06
    oded
    0.06
    æµ®
    0.06
    undy
    0.06
    ä¸Ķ
    0.06
    å®ļ为
    0.06
    adrat
    0.06
    izza
    0.06
    Activations Density 0.023%

    No Known Activations