© 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. 21498
    Prev
    Next
    INDEX
    Explanations

    overheard, witnessed, heard

    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
    uteur
    -0.06
    fis
    -0.06
    roh
    -0.06
    ëĸ»
    -0.06
    inspection
    -0.06
    鬼
    -0.06
    веÑĤа
    -0.06
    éªĭ
    -0.06
    .rem
    -0.06
    acons
    -0.06
    POSITIVE LOGITS
    æĪª
    0.06
     villain
    0.05
     Undert
    0.05
    èĩ³æѤ
    0.05
     ÑĢаÑģп
    0.05
     bis
    0.05
    æĪªåıĸ
    0.05
    ants
    0.05
     entre
    0.05
    åº
    0.05
    Activations Density 0.005%

    No Known Activations