© 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. 40917
    Prev
    Next
    INDEX
    Explanations

    part of complex words or phrases

    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
    åĴĮéĶĢåĶ®
    -0.07
    åħ·æľī以ä¸ĭ
    -0.07
    ãģıãĤī
    -0.07
    æĽĻ
    -0.06
    大家好
    -0.06
    ctor
    -0.06
    cil
    -0.06
    ktor
    -0.06
    ÑĪÑĮ
    -0.06
    港澳åı°
    -0.06
    POSITIVE LOGITS
    amed
    0.08
    erson
    0.08
    .yahoo
    0.08
    боÑĢÑĭ
    0.07
    æĹ¥æ¸¸
    0.07
    otope
    0.07
    éļ¾çĤ¹éĹ®é¢ĺ
    0.07
    acos
    0.07
    ovich
    0.07
    KG
    0.07
    Activations Density 1.207%

    No Known Activations