© 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. 21536
    Prev
    Next
    INDEX
    Explanations

    numbers and units of measurement

    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
    ét
    -0.06
    s
    -0.06
     pipeline
    -0.05
    .pipeline
    -0.05
    جÙĪ
    -0.05
     вÑĬз
    -0.05
    ÑĮÑİ
    -0.05
     filtered
    -0.05
     representing
    -0.05
    åIJĽåŃIJ
    -0.05
    POSITIVE LOGITS
    acle
    0.06
    reh
    0.05
    /T
    0.05
    hut
    0.05
    пол
    0.05
    çļĦæ¬²æľĽ
    0.05
     Evidence
    0.05
    ellen
    0.05
    arp
    0.05
    åĻ¨åħ·
    0.05
    Activations Density 0.002%

    No Known Activations