© 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. 19054
    Prev
    Next
    INDEX
    Explanations

    `npm run` commands

    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
    -0.07
    ward
    -0.07
    /
    -0.06
    ,
    -0.05
    wards
    -0.05
    o
    -0.05
     v
    -0.05
    -
    -0.05
    v
    -0.05
    ?
    -0.05
    POSITIVE LOGITS
    etine
    0.08
     denun
    0.07
    bau
    0.07
    ÑĤвоÑĢÑı
    0.07
    è¡ĮçĤº
    0.07
    etik
    0.07
    etica
    0.07
    etts
    0.07
     izb
    0.07
    itti
    0.07
    Activations Density 0.005%

    No Known Activations