© 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. 21394
    Prev
    Next
    INDEX
    Explanations

    code blocks or comments

    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
    å°ıå¹³
    -0.07
    chino
    -0.06
    haven
    -0.06
    icola
    -0.06
     Related
    -0.06
     lu
    -0.06
    giv
    -0.05
    ibly
    -0.05
    jÄħ
    -0.05
    头
    -0.05
    POSITIVE LOGITS
    esos
    0.05
    ensione
    0.05
    unicipio
    0.05
    esis
    0.05
    upes
    0.05
    eing
    0.05
    å®ĮçĴ§
    0.05
     triggered
    0.05
    ipot
    0.05
    unyi
    0.05
    Activations Density 0.005%

    No Known Activations