© 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. 15442
    Prev
    Next
    INDEX
    Explanations

    Server.Items

    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
    ostar
    -0.07
    axe
    -0.07
     *:
    -0.07
    便æĺ¯
    -0.07
    ç«Łæĺ¯
    -0.06
    å·¥ä½ľå§Ķåijĺä¼ļ
    -0.06
    اخ
    -0.06
     SetLastError
    -0.06
     pina
    -0.06
    åİŁæĺ¯
    -0.06
    POSITIVE LOGITS
    çĶ±æѤ
    0.08
    大大å°ı
    0.07
    elo
    0.07
    arkin
    0.07
    说ä¸į
    0.07
    æįŁ
    0.07
    eps
    0.07
    lare
    0.07
    Č
    0.07
    éĽĨä¸ŃçļĦ
    0.07
    Activations Density 0.004%

    No Known Activations