© 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. 21034
    Prev
    Next
    INDEX
    Explanations

    roman numerals II, III, VI

    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
    egr
    -0.07
    ño
    -0.06
    HOLDER
    -0.06
    lands
    -0.06
    ible
    -0.06
    land
    -0.06
    ждÑĥÑİ
    -0.06
    impan
    -0.06
    ments
    -0.06
    abit
    -0.06
    POSITIVE LOGITS
    ound
    0.07
    Ùĩا
    0.07
     ÑĥдобÑģÑĤва
    0.07
    à¸¹à¸Ľ
    0.06
     желании
    0.06
    ÑģÑĤе
    0.06
    cii
    0.06
    ÙĩاÛĮÛĮ
    0.06
    istere
    0.06
    blink
    0.06
    Activations Density 0.049%

    No Known Activations