© 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. 39774
    Prev
    Next
    INDEX
    Explanations

    merch, nuclear medicine, responses

    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
     chances
    -0.09
    åĴĮæĹ¥æľ¬
    -0.08
     Ariel
    -0.08
     ÑĪанÑģ
    -0.07
    iard
    -0.07
    .NewReader
    -0.07
    chnik
    -0.07
    ble
    -0.07
    дже
    -0.07
     chance
    -0.07
    POSITIVE LOGITS
    èĨ³
    0.08
     Mand
    0.07
    вÑĮÑİ
    0.07
     pil
    0.07
    éĢļ讯å½ķ
    0.06
    çĽĹ
    0.06
     anf
    0.06
    باد
    0.06
    è¨Ģè¡Į
    0.06
     flexGrow
    0.06
    Activations Density 0.010%

    No Known Activations