© 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. 10892
    Prev
    Next
    INDEX
    Explanations

    energy, body, health, healing

    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
    itut
    -0.07
    punt
    -0.07
    åĩĦåĩī
    -0.07
     exploit
    -0.07
     concurr
    -0.07
    oji
    -0.07
     Nationwide
    -0.07
    ardi
    -0.07
    ä¸įåĽł
    -0.07
    çħ½
    -0.06
    POSITIVE LOGITS
     healing
    0.10
    çĸĹæĦĪ
    0.09
    çļĦèĥ½éĩı
    0.09
     Healing
    0.09
    èĥ½éĩıçļĦ
    0.09
    转åĮĸ
    0.08
    èĥ½éĩı
    0.08
    转åĮĸçļĦ
    0.08
    alchemy
    0.08
     patter
    0.08
    Activations Density 0.067%

    No Known Activations