© 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. 31227
    Prev
    Next
    INDEX
    Explanations

    config, name, 0

    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
    astia
    -0.10
    trys
    -0.08
    иÑģк
    -0.07
    çī¹æ´¾
    -0.07
    oky
    -0.07
    trice
    -0.07
    olph
    -0.07
    iskan
    -0.07
     renouvel
    -0.07
    ông
    -0.07
    POSITIVE LOGITS
    allen
    0.07
     Synthetic
    0.07
     synthetic
    0.06
    åĪĨä¹ĭ
    0.06
     imperial
    0.06
    tä
    0.06
    ä¸ĢåĪĨ
    0.06
    è¦ģ约
    0.06
    æĴķè£Ĥ
    0.06
    jero
    0.06
    Activations Density 0.001%

    No Known Activations