© 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. 19320
    Prev
    Next
    INDEX
    Explanations

    GLFW, GUI, Unity, hepatocyte

    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
    -0.06
    osaic
    -0.05
    opher
    -0.05
     "
    -0.05
    /java
    -0.05
     Blast
    -0.05
    !
    -0.05
     restriction
    -0.05
    |
    -0.05
    axon
    -0.04
    POSITIVE LOGITS
    dach
    0.08
    годно
    0.07
    skr
    0.07
     akr
    0.07
     insp
    0.07
     оÑĤв
    0.06
    é½¢
    0.06
     –**
    0.06
    niv
    0.06
    utilise
    0.06
    Activations Density 0.017%

    No Known Activations