© 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. 22263
    Prev
    Next
    INDEX
    Explanations

    event

    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
    évén
    -0.07
    endara
    -0.07
     eventType
    -0.07
     наказа
    -0.07
    glich
    -0.07
    cantidad
    -0.07
     createState
    -0.07
    ذا
    -0.06
    érieur
    -0.06
    äºĭ件ä¸Ń
    -0.06
    POSITIVE LOGITS
    let
    0.06
    ib
    0.06
    hand
    0.06
    认
    0.06
    ew
    0.06
     hand
    0.05
     over
    0.05
     I
    0.05
     de
    0.05
    ui
    0.05
    Activations Density 0.012%

    No Known Activations