© 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. 17857
    Prev
    Next
    INDEX
    Explanations

    numbers and filenames

    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
    utan
    -0.06
    ä¸Ģ说
    -0.06
    umine
    -0.05
    bum
    -0.05
    inese
    -0.05
     Bloom
    -0.05
    ampton
    -0.05
     techniques
    -0.05
     participants
    -0.05
    ombine
    -0.05
    POSITIVE LOGITS
    lette
    0.06
    ervers
    0.06
    -copy
    0.06
    奢
    0.06
    ariah
    0.05
    rich
    0.05
     Priv
    0.05
    esz
    0.05
     jog
    0.05
    ä½ĵç³»åĴĮ
    0.05
    Activations Density 0.004%

    No Known Activations