© 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. 8713
    Prev
    Next
    INDEX
    Explanations

    button type info

    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
     coordinating
    -0.08
    åħĭç¦ı
    -0.07
    IGH
    -0.07
     Coordin
    -0.07
    æĮĩå®ļçļĦ
    -0.07
    باÙĨ
    -0.07
     shall
    -0.07
    ]\\
    -0.07
    ÑĮем
    -0.07
     coordinated
    -0.07
    POSITIVE LOGITS
     exactly
    0.09
    è¿ĻæŃ£æĺ¯
    0.09
    æŃ£æĺ¯
    0.08
     Exactly
    0.08
    Exactly
    0.08
    æŃ£å¥½
    0.08
    ä¹ŁæŃ£æĺ¯
    0.07
     genau
    0.07
    讲ä¹ī
    0.07
    çĻ¾åĢį
    0.07
    Activations Density 0.003%

    No Known Activations