© 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. 15633
    Prev
    Next
    INDEX
    Explanations

    contraction 'd

    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
    obie
    -0.07
    оба
    -0.07
    ancel
    -0.07
    æĸ°åĮĹ
    -0.06
    å³
    -0.06
    oked
    -0.06
     règ
    -0.06
    éĤªéŃĶ
    -0.06
    enance
    -0.06
    obile
    -0.06
    POSITIVE LOGITS
    orn
    0.07
    æŶå°Ĩ
    0.07
    åł°
    0.07
    ä¸įè¦ģæĬĬ
    0.07
    羽翼
    0.06
    ä¸į对
    0.06
    éĢīæĭ©ä¸įåIJĮçļĦ
    0.06
    NIK
    0.06
    å¾ĹæĽ´åĬł
    0.06
    igue
    0.06
    Activations Density 0.079%

    No Known Activations