© 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. 21939
    Prev
    Next
    INDEX
    Explanations

    Life, Barrel, Wizard, castle, Lewis, Passport, Jobs

    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
    باط
    -0.05
    inki
    -0.05
    integr
    -0.05
    !("{
    -0.05
    åĸľ
    -0.05
    jär
    -0.05
    第åįģ
    -0.05
    zü
    -0.05
    æ¯Ķå¦Ĥ说
    -0.05
    è¸Ĭè·ĥ
    -0.05
    POSITIVE LOGITS
    ž
    0.06
    /do
    0.06
    antos
    0.05
    box
    0.05
    线ä¸ĬçļĦ
    0.05
    assar
    0.05
    anto
    0.05
    illa
    0.05
    uche
    0.05
     вик
    0.05
    Activations Density 0.004%

    No Known Activations