© 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. 21351
    Prev
    Next
    INDEX
    Explanations

    opposition of

    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
    reas
    -0.05
     Presentation
    -0.05
    åijĪçİ°åĩº
    -0.05
     kav
    -0.05
    cles
    -0.05
     korupsi
    -0.05
    贪污
    -0.05
    ervations
    -0.05
    aign
    -0.05
    订éĺħ
    -0.05
    POSITIVE LOGITS
    anz
    0.07
     اÙĦجÙħ
    0.06
    iehen
    0.06
    arit
    0.06
     expedi
    0.06
    ben
    0.05
    imal
    0.05
    xit
    0.05
    anzi
    0.05
     notwithstanding
    0.05
    Activations Density 0.002%

    No Known Activations