© 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. 31824
    Prev
    Next
    INDEX
    Explanations

    construction/structure words

    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
    èĤ
    -0.06
    .compile
    -0.06
    è¿Ľæł¡åĽŃ
    -0.06
    pile
    -0.06
     Lans
    -0.06
     recorr
    -0.06
    çĪ±ä¸Ĭ
    -0.06
    ç²
    -0.06
    辩
    -0.06
    uild
    -0.06
    POSITIVE LOGITS
    åľ¨ä¸ĭ
    0.08
    umbu
    0.08
    "struct
    0.07
    Ĥ¹
    0.07
    ıkl
    0.07
    èį·
    0.07
    truct
    0.07
    бÑĥдÑĮ
    0.07
    æĦļ人
    0.07
    ofday
    0.07
    Activations Density 0.006%

    No Known Activations