© 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. 17211
    Prev
    Next
    INDEX
    Explanations

    tag, assay, partner, store, facility

    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
    alu
    -0.07
    ignes
    -0.07
    anca
    -0.07
    åĬłåĭĴ
    -0.07
    -thumbnails
    -0.07
    burgh
    -0.06
    ergia
    -0.06
    anes
    -0.06
    aglia
    -0.06
    illus
    -0.06
    POSITIVE LOGITS
    hofer
    0.08
    ãģ«ãĤĪãģ£ãģ¦ãģ¯
    0.08
    ëıĮ
    0.07
    endt
    0.07
    åĪĨ许
    0.07
    ä¼Ĭå§ĭ
    0.07
    वार
    0.07
    ivating
    0.07
     вел
    0.07
     ÐĴой
    0.07
    Activations Density 0.735%

    No Known Activations