© 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. 17561
    Prev
    Next
    INDEX
    Explanations

    home care and learning

    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
     rhetorical
    -0.07
    为éļ¾
    -0.07
    çĪ±æĥľ
    -0.07
    este
    -0.07
    rette
    -0.07
     thừa
    -0.07
    mey
    -0.07
    ember
    -0.06
    estan
    -0.06
    ³
    -0.06
    POSITIVE LOGITS
    /home
    0.12
    -home
    0.11
     home
    0.10
    home
    0.10
    èĩªåѦ
    0.10
    /Home
    0.10
    æĪĸåľ¨
    0.09
    (home
    0.09
     domic
    0.09
    remote
    0.09
    Activations Density 0.220%

    No Known Activations