© 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. 31112
    Prev
    Next
    INDEX
    Explanations

    first part

    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
    æī¬éķ¿
    -0.07
    ikus
    -0.07
    éļ¾æĺĵ
    -0.07
     Stout
    -0.07
    åĮ¿
    -0.06
    /problems
    -0.06
    çĨ¬å¤ľ
    -0.06
    è¡¥ä¸ģ
    -0.06
    àºį
    -0.06
    วาร
    -0.06
    POSITIVE LOGITS
     Dedicated
    0.10
     dedicated
    0.10
     dedicate
    0.09
     dedic
    0.09
    åı¯ä»¥çĶ¨æĿ¥
    0.08
     reserved
    0.08
    åı¯çĶ¨äºİ
    0.08
     dedicada
    0.08
     devoted
    0.08
    çķĻåĩº
    0.08
    Activations Density 0.092%

    No Known Activations