© 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. 20363
    Prev
    Next
    INDEX
    Explanations

    code snippets including keywords like var

    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
    ather
    -0.06
    çļĦä¸Ģ大
    -0.06
    odo
    -0.05
     Nonostante
    -0.05
    amed
    -0.05
    onar
    -0.05
    ç«ŀäºīæ¿ĢçĥĪ
    -0.05
    egen
    -0.05
    ius
    -0.05
     sorta
    -0.05
    POSITIVE LOGITS
    пÑĢаве
    0.06
    éĤ£å¤´
    0.05
    apor
    0.05
    artos
    0.05
    apura
    0.05
    вÑĥ
    0.05
    alet
    0.05
    å±ħ
    0.05
    çĸĹ
    0.05
     Apps
    0.05
    Activations Density 0.175%

    No Known Activations