© 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. 40561
    Prev
    Next
    INDEX
    Explanations

    list

    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
    ↵                        ↵
    -0.07
    ovin
    -0.07
    åı¯è§ģ
    -0.07
    urah
    -0.07
     ↵            ↵
    -0.07
    ordial
    -0.07
    ecker
    -0.06
    kle
    -0.06
    olland
    -0.06
    /Private
    -0.06
    POSITIVE LOGITS
    acher
    0.07
    è¡Įäºij
    0.07
    kit
    0.07
    æī¯
    0.07
    iaga
    0.06
    Licensed
    0.06
    ubb
    0.06
    ãģĦãģį
    0.06
    éģ½
    0.06
    olds
    0.06
    Activations Density 0.004%

    No Known Activations