© 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. 19876
    Prev
    Next
    INDEX
    Explanations

    induced contraction

    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
    agar
    -0.07
    èĢĮå°±
    -0.06
    SEX
    -0.06
     Kinderg
    -0.06
     dédiée
    -0.06
     Implements
    -0.06
    åı¦å¤ĸä¸Ģç§į
    -0.06
    ohen
    -0.06
    клада
    -0.05
    amy
    -0.05
    POSITIVE LOGITS
    ivers
    0.06
    èĬĤ
    0.05
    because
    0.05
     Because
    0.05
    itesi
    0.05
    åĽłåħ¶
    0.05
    rike
    0.05
    åĽłä¸ºå®ĥ
    0.05
     entrambe
    0.05
    ContentLoaded
    0.05
    Activations Density 0.008%

    No Known Activations