© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50275
    Prev
    Next
    INDEX
    Explanations

    roleplay, play, succeed, cooperate

    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
    åĴĢ
    -0.08
    ifi
    -0.07
    uppy
    -0.07
    Aggregate
    -0.07
    æĶĢçĻ»
    -0.07
    çħ§æł·
    -0.06
    èģļ
    -0.06
    åıĹç²¾åįµ
    -0.06
    缤
    -0.06
    å¿¿
    -0.06
    POSITIVE LOGITS
    ĮĢ
    0.08
    ucci
    0.08
    utters
    0.08
    eed
    0.07
    ç¦ģ
    0.07
    ç¾İåĽ¾
    0.07
    PTH
    0.07
    rompt
    0.07
     regul
    0.07
    bris
    0.07
    Activations Density 0.046%

    No Known Activations