© 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. 2452
    Prev
    Next
    INDEX
    Explanations

    prepared, dropping, undergone

    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
    estat
    -0.07
    人士
    -0.07
    бÑĢо
    -0.07
     Goods
    -0.07
    verity
    -0.07
    æ··æ··
    -0.07
    achr
    -0.07
    udded
    -0.07
    adic
    -0.07
    æļ«
    -0.07
    POSITIVE LOGITS
    èm
    0.07
    ļ
    0.07
    -feed
    0.06
    ugging
    0.06
    éĴ©
    0.06
     Mauro
    0.06
    .def
    0.06
    hop
    0.06
    omi
    0.06
    cmd
    0.06
    Activations Density 0.211%

    No Known Activations