© 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. 64385
    Prev
    Next
    INDEX
    Explanations

    tuple access

    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
    rapper
    -0.08
    autop
    -0.07
    æĭł
    -0.07
     lazada
    -0.07
    μαÏĦα
    -0.07
     trap
    -0.07
     Licenci
    -0.07
    LEY
    -0.07
    ikov
    -0.06
    nhard
    -0.06
    POSITIVE LOGITS
    anye
    0.07
    <hr
    0.07
    zt
    0.07
    бил
    0.07
    潺
    0.07
    æīij
    0.07
    andal
    0.07
    arak
    0.07
     reciprocal
    0.06
    æģ¶
    0.06
    Activations Density 0.006%

    No Known Activations