© 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. 12719
    Prev
    Next
    INDEX
    Explanations

    invention relates

    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
    ync
    -0.07
    åį³åĪ°
    -0.07
    让çĶŁæ´»
    -0.06
    idez
    -0.06
    yal
    -0.06
    yg
    -0.06
    .cy
    -0.06
    iding
    -0.06
    ops
    -0.06
     Pro
    -0.06
    POSITIVE LOGITS
    æīĢéľĢè¦ģ
    0.08
    uket
    0.08
    ÙĪÙĦد
    0.07
    æīĢéľĢè¦ģçļĦ
    0.07
    SCP
    0.07
    angu
    0.07
    åĴĮæľīåħ³
    0.07
    allen
    0.07
    裳
    0.07
    hluk
    0.07
    Activations Density 0.001%

    No Known Activations