© 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. 26052
    Prev
    Next
    INDEX
    Explanations

    combined

    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
    AHAN
    -0.08
    绣ä¸ĢçļĦ
    -0.08
    chung
    -0.08
     Feliz
    -0.08
    yper
    -0.07
    ysi
    -0.07
    åĭĴæĸ¯
    -0.07
    ysel
    -0.07
    æĺł
    -0.07
    æī¹
    -0.07
    POSITIVE LOGITS
    åĬ©
    0.07
    ogan
    0.07
    ä¸įæĪIJ
    0.07
    åIJĪä½ľçĶ¨
    0.07
    auc
    0.07
    è¦ģä¸į
    0.06
    åij½
    0.06
    ini
    0.06
     Hin
    0.06
    ulton
    0.06
    Activations Density 0.004%

    No Known Activations