© 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. 4148
    Prev
    Next
    INDEX
    Explanations

    author names and years

    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
    ĵĺ
    -0.09
    exion
    -0.08
    æ²ŁæĿij
    -0.07
    Ú¯ÙĦ
    -0.07
    ieder
    -0.07
    åѦæľīæīĢ
    -0.07
    Ùħت
    -0.07
    illage
    -0.07
    λεκ
    -0.07
    æĸĹå¿Ĺ
    -0.07
    POSITIVE LOGITS
    ath
    0.07
    roll
    0.07
     Subcommittee
    0.06
    W
    0.06
     ë§Īì°¬
    0.06
    rops
    0.06
     Сооб
    0.06
     Pregun
    0.06
    åĪ©
    0.06
    -deals
    0.06
    Activations Density 0.090%

    No Known Activations