© 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. 18426
    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
    thouse
    -0.09
    dorf
    -0.08
    ä¸īåľ°
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    zub
    -0.08
     ÑĢазвеÑĢ
    -0.08
    ordert
    -0.08
    stell
    -0.08
    صاب
    -0.07
     Mendes
    -0.07
    POSITIVE LOGITS
     shielding
    0.10
    å±ıèĶ½
    0.08
    å±ıé£İ
    0.08
    Shield
    0.08
     shields
    0.07
    èĹ©
    0.07
    ä¿ĿæĬ¤ä½ľçĶ¨
    0.07
    éĽĨåĽ¢
    0.07
    é¼
    0.07
     shield
    0.06
    Activations Density 0.000%

    No Known Activations