© 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. 16438
    Prev
    Next
    INDEX
    Explanations

    origin and time

    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
     Kuk
    -0.08
    ams
    -0.07
    Forever
    -0.07
    iché
    -0.07
    orama
    -0.07
    igli
    -0.07
    INGTON
    -0.06
    dem
    -0.06
     haste
    -0.06
    缮åīįçļĦ
    -0.06
    POSITIVE LOGITS
    æĹ©åľ¨
    0.13
    æĹ©æľī
    0.13
    éĽıå½¢
    0.11
    æĹ©
    0.11
    æľĢæĹ©çļĦ
    0.11
    å¾ĪæĹ©å°±
    0.11
     earliest
    0.11
    æľĢæĹ©
    0.10
    æĹ©å°±
    0.10
    èIJĮèĬ½
    0.09
    Activations Density 0.545%

    No Known Activations