© 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. 20978
    Prev
    Next
    INDEX
    Explanations

    alternative

    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
    ness
    -0.08
    ment
    -0.07
    tral
    -0.07
    ickle
    -0.06
    NESS
    -0.06
    MENT
    -0.06
    lanj
    -0.06
    ments
    -0.06
    lü
    -0.06
    عÙĦÙĨت
    -0.06
    POSITIVE LOGITS
    tul
    0.06
    ide
    0.06
    tabel
    0.06
    aad
    0.06
    vv
    0.05
    ../../../../
    0.05
    оÑģÑĤ
    0.05
    indir
    0.05
    à¹īาà¸ĩ
    0.05
    اء
    0.05
    Activations Density 0.011%

    No Known Activations