© 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. 18323
    Prev
    Next
    INDEX
    Explanations

    related to errors or loading/completion states

    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
    ciano
    -0.09
    »
    -0.09
     Ayd
    -0.08
    nikov
    -0.08
    lick
    -0.08
    xbc
    -0.07
    taire
    -0.07
    qrt
    -0.07
    çŃīåįķä½į
    -0.07
    å¾Ī强çļĦ
    -0.07
    POSITIVE LOGITS
    ogat
    0.07
    æĬµ
    0.07
    åĮ¿
    0.06
     зака
    0.06
    çŁ¥
    0.06
    æĹĹé¼ĵ
    0.06
    edException
    0.06
    èĩªåı¤
    0.06
    ç½
    0.05
    uer
    0.05
    Activations Density 0.399%

    No Known Activations