© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17429
    Prev
    Next
    INDEX
    Explanations

    `security oauth`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hello
    -0.06
    å¦Ĥä¸Ģ
    -0.06
    _hello
    -0.05
    æĹ¥åĴĮ
    -0.05
    amet
    -0.05
     Hos
    -0.05
    sti
    -0.05
     hello
    -0.05
    çİī
    -0.05
    .simple
    -0.05
    POSITIVE LOGITS
    )|(
    0.06
    ฤษà¸İ
    0.05
    enan
    0.05
    以åıĬ缸åħ³
    0.05
    çªĿ
    0.05
    dah
    0.05
     ç§ģ
    0.05
    为è¾ħ
    0.05
    seb
    0.05
    ienen
    0.05
    Activations Density 0.193%

    No Known Activations