© 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. 8131
    Prev
    Next
    INDEX
    Explanations

    numbers and boolean types

    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
    stieg
    -0.07
    OrDefault
    -0.07
    æ¡£
    -0.06
     Stamm
    -0.06
    解åĨ³å®ŀéĻħ
    -0.06
     Lov
    -0.06
    STER
    -0.06
    èŃ²
    -0.06
    转
    -0.06
    íĮħ
    -0.06
    POSITIVE LOGITS
    汹汹
    0.08
    alisi
    0.07
    emm
    0.07
    æĿİåħĪçĶŁ
    0.07
    иден
    0.07
    çĵ®
    0.07
    ColumnType
    0.07
    ught
    0.07
    okka
    0.07
    INV
    0.07
    Activations Density 0.027%

    No Known Activations