© 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. 25991
    Prev
    Next
    INDEX
    Explanations

    5' end

    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
    æĪĸå°ij
    -0.08
    æĪĸä¸į
    -0.08
    ذج
    -0.08
    enko
    -0.07
    ett
    -0.07
     Rows
    -0.07
    okol
    -0.07
    rels
    -0.07
    utch
    -0.07
    åĵ¥
    -0.07
    POSITIVE LOGITS
    ward
    0.09
    most
    0.08
    -most
    0.08
    adini
    0.07
    ¿
    0.07
    æľīä½ł
    0.07
    端çļĦ
    0.07
    ีย
    0.07
    erso
    0.07
    adem
    0.07
    Activations Density 0.025%

    No Known Activations