© 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. 21299
    Prev
    Next
    INDEX
    Explanations

    development, marketing, and services

    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
    è¨
    -0.06
    ned
    -0.06
    waan
    -0.06
    plas
    -0.05
    çĦ¦
    -0.05
    红èī²çļĦ
    -0.05
    ischem
    -0.05
    edList
    -0.05
     FETCH
    -0.05
    manos
    -0.05
    POSITIVE LOGITS
    ulet
    0.05
     masque
    0.05
    Mass
    0.05
    æıIJçIJ´
    0.05
    oul
    0.05
    asp
    0.05
    ÙĪاÙĨ
    0.05
    aning
    0.05
    way
    0.05
    p
    0.05
    Activations Density 0.020%

    No Known Activations