© 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. 42809
    Prev
    Next
    INDEX
    Explanations

    web engine or VR

    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
    åıijå±ķä¸İ
    -0.06
    æĢ¥
    -0.06
    ãĢĪ
    -0.06
    ular
    -0.05
    æ²ĥæĸ¯
    -0.05
    çĮ®
    -0.05
    obet
    -0.05
    ä¸įä»ħ
    -0.05
    禹
    -0.05
     Rom
    -0.05
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.10
    bows
    0.08
    zos
    0.08
    xie
    0.08
    ça
    0.08
    hower
    0.08
    hud
    0.08
    éĺ¿æĭī伯
    0.08
     ìĦŃ
    0.08
    cide
    0.08
    Activations Density 0.677%

    No Known Activations