© 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. 27803
    Prev
    Next
    INDEX
    Explanations

    locations and institutions

    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
    åħ¨æĿij
    -0.07
    elaar
    -0.07
    ä¸įèĩ³
    -0.07
     thô
    -0.07
    浩浩
    -0.06
    å¿ĥåľ°
    -0.06
    ä¸Ģè¡Į
    -0.06
     getOrder
    -0.06
    ÙĪØŃØ©
    -0.06
     materials
    -0.06
    POSITIVE LOGITS
    à¸Ĺัà¹Īà¸§à¸Ľà¸£à¸°à¹Ģà¸Ĺศ
    0.11
    åĪĨå¸ĥåľ¨
    0.11
    ä¸Ģ个个
    0.11
    éģįå¸ĥ
    0.11
    çĽ¸æľĽ
    0.10
    ë§Īëĭ¤
    0.10
    åĪĨå¸ĥäºİ
    0.10
    åIJĦåħ·
    0.10
    è¿ĻäºĽåľ°æĸ¹
    0.10
    大å¤ļ
    0.09
    Activations Density 0.552%

    No Known Activations