© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20037
    Prev
    Next
    INDEX
    Explanations

    privilege escalation

    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
    aber
    -0.07
    éĿ¢ä¸ĬçļĦ
    -0.06
    elle
    -0.06
     absoluto
    -0.05
    æĭŁ
    -0.05
    airs
    -0.05
     saz
    -0.05
    imson
    -0.05
    åľ¨ä¸Ģå®ļ
    -0.05
    ellan
    -0.05
    POSITIVE LOGITS
    à¸ķัว
    0.07
    çħ§
    0.06
    xic
    0.06
    itness
    0.06
     super
    0.05
    íĥľ
    0.05
    çħ§çĿĢ
    0.05
     phủ
    0.05
    }//
    0.05
    ondi
    0.05
    Activations Density 0.002%

    No Known Activations