© 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. 13854
    Prev
    Next
    INDEX
    Explanations

    languages and terms

    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
    ÃŃo
    -0.07
    enery
    -0.07
    è¿ŀçݯ
    -0.07
    -cn
    -0.07
    ponder
    -0.07
    Dst
    -0.07
     Fabriz
    -0.06
    ãĤ·ãĥ§
    -0.06
    iz
    -0.06
    enius
    -0.06
    POSITIVE LOGITS
    emain
    0.07
    arau
    0.07
    èī²
    0.06
    á»ıng
    0.06
    éĻį
    0.06
    ussa
    0.06
    radas
    0.06
    禹
    0.06
    icke
    0.06
    angu
    0.06
    Activations Density 0.027%

    No Known Activations