© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22615
    Prev
    Next
    INDEX
    Explanations

    quantifying progression

    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
    Negative Logits
    eceÄŁ
    -0.05
    íļĮ
    -0.05
    宸
    -0.05
    ocity
    -0.05
    lights
    -0.05
     Onze
    -0.05
    åħĭåĬĽ
    -0.04
    orse
    -0.04
     ausge
    -0.04
     temper
    -0.04
    POSITIVE LOGITS
    ä¸Ģä¸ĭ
    0.06
    huizen
    0.06
    ìĨį
    0.06
    Originally
    0.06
    uddenly
    0.06
    atk
    0.06
    ;c
    0.06
     nÆ°Æ¡ng
    0.06
     beho
    0.06
    ittäin
    0.06
    Activations Density 0.004%

    No Known Activations