© 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. 20386
    Prev
    Next
    INDEX
    Explanations

    everyday life

    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
    ê¹IJ
    -0.08
     gespi
    -0.07
    indir
    -0.07
    elat
    -0.07
    impa
    -0.07
    ellos
    -0.07
    à¸Ĺาà¸ĩà¸ģาร
    -0.07
    ousy
    -0.07
    -fire
    -0.07
    ifestyles
    -0.07
    POSITIVE LOGITS
    spre
    0.06
    деÑģÑıÑĤ
    0.05
    à¸Ļาà¸Ļ
    0.05
    erm
    0.05
    urance
    0.05
    erson
    0.05
    rench
    0.05
    s
    0.05
    ÛĮ
    0.05
     else
    0.05
    Activations Density 0.005%

    No Known Activations