© 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. 60835
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ota
    -0.08
    ydd
    -0.07
    ymi
    -0.07
    åīĬ
    -0.07
    ä¼¼
    -0.06
    å¾ĢæĹ¥
    -0.06
    szyst
    -0.06
    .psi
    -0.06
    iem
    -0.06
    yme
    -0.06
    POSITIVE LOGITS
    schlag
    0.08
    Ñıн
    0.08
    enes
    0.08
     непÑĢо
    0.08
    incid
    0.07
    åĪ©äºļ
    0.07
    ä¹ł
    0.07
    udging
    0.07
    ç§ģæĪ¿
    0.07
    áºŃu
    0.07
    Activations Density 0.000%

    No Known Activations