© 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. 58544
    Prev
    Next
    INDEX
    Explanations

    first/second/next/other/both

    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
    ķĮ
    -0.08
    æī®
    -0.07
    elian
    -0.07
    该åĨħ容
    -0.07
    มà¸ĩ
    -0.07
    CCC
    -0.06
    iban
    -0.06
    ä¸ĢåĪĩçļĦ
    -0.06
    ouden
    -0.06
    èŀĥ
    -0.06
    POSITIVE LOGITS
    izzo
    0.08
    _REGISTRY
    0.08
    pekt
    0.08
    inkin
    0.07
    çıŃåŃIJ
    0.07
    ambi
    0.07
    byname
    0.07
    amera
    0.07
    roma
    0.07
    ä¸Ģåı·
    0.07
    Activations Density 0.823%

    No Known Activations