© 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. 64900
    Prev
    Next
    INDEX
    Explanations

    pre-owned watch

    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
    å¦ĤèĬ±
    -0.08
    ENTA
    -0.08
    èĭĩ
    -0.08
    å¾ħåĪ°
    -0.08
    OfYear
    -0.07
    ros
    -0.07
    uvia
    -0.07
    inique
    -0.07
    é»Ħæ²Ļ
    -0.07
    cae
    -0.07
    POSITIVE LOGITS
    aton
    0.06
    ize
    0.06
    ãĢĤï¼Ī
    0.06
    æ°¸è¿ľ
    0.06
    è¿ŁæĹ©
    0.06
    0.06
    åŃIJ
    0.06
    æijĩæijĨ
    0.06
    åĦ¿
    0.06
    ��
    0.06
    Activations Density 0.018%

    No Known Activations