© 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. 10078
    Prev
    Next
    INDEX
    Explanations

    equation equals 0

    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
    ק×Ķ
    -0.08
    à³įದ
    -0.08
    注æĦıäºĨ
    -0.08
    pired
    -0.07
    ì±
    -0.07
     Biro
    -0.07
    礼
    -0.07
    üns
    -0.07
    /meta
    -0.07
    ioctl
    -0.07
    POSITIVE LOGITS
    ÃŃp
    0.06
    çĤ¹è¿Ľè¡Į
    0.06
    icit
    0.06
    åĪĿæŃ¥
    0.06
    onne
    0.06
    iloc
    0.06
    æīĢåľ¨
    0.06
    ÑĢÑİ
    0.06
    /non
    0.06
    大åѦ
    0.06
    Activations Density 0.002%

    No Known Activations