© 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. 17218
    Prev
    Next
    INDEX
    Explanations

    early referring to incidents

    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
    acos
    -0.06
    è£¸éľ²
    -0.06
    leman
    -0.05
     Obec
    -0.05
    elos
    -0.05
    /stretch
    -0.05
    ãĥ©ãĤ¹
    -0.05
    chand
    -0.05
    йка
    -0.05
     Lice
    -0.05
    POSITIVE LOGITS
    richten
    0.06
     Demand
    0.05
    ugg
    0.05
    álló
    0.05
    wär
    0.05
    سازÛĮ
    0.05
    Demand
    0.05
    åĨ²çªģ
    0.05
    roupon
    0.05
    æį¢æĿ¥
    0.05
    Activations Density 0.001%

    No Known Activations