© 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. 64522
    Prev
    Next
    INDEX
    Explanations

    parentheses and code

    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
    oÄį
    -0.07
    tml
    -0.06
    {}.
    -0.06
    odor
    -0.06
    anlage
    -0.06
    inga
    -0.06
    enticator
    -0.06
    artal
    -0.06
    Ùĩ
    -0.06
    æĥħæĦı
    -0.06
    POSITIVE LOGITS
    ombe
    0.08
    ity
    0.08
    изи
    0.08
    åľ°è¢«
    0.08
    ierce
    0.08
    istration
    0.08
    oci
    0.08
    mith
    0.07
    ledge
    0.07
    ians
    0.07
    Activations Density 0.026%

    No Known Activations