© 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. 21094
    Prev
    Next
    INDEX
    Explanations

    numbers and code symbols

    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
    íĦ´
    -0.06
    ALAR
    -0.05
    æĺ¯éĿł
    -0.05
    اعات
    -0.05
    altet
    -0.05
    ickness
    -0.05
    座
    -0.05
    hum
    -0.05
    imas
    -0.05
    иÑģÑĤо
    -0.05
    POSITIVE LOGITS
    çīĮçļĦ
    0.06
    ihn
    0.05
    bst
    0.05
    éĢ¼äºº
    0.05
    .setProperty
    0.05
     bem
    0.05
    õt
    0.05
    vore
    0.05
    oge
    0.05
    istin
    0.05
    Activations Density 0.053%

    No Known Activations