© 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. 21500
    Prev
    Next
    INDEX
    Explanations

    present invention

    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
    ĭ
    -0.06
    oucher
    -0.06
     increment
    -0.05
     Spec
    -0.05
    模åĿĹåĮĸ
    -0.05
    ãĢģ“
    -0.05
     Increment
    -0.05
    Pres
    -0.05
     Vic
    -0.05
     Sim
    -0.04
    POSITIVE LOGITS
    çºł
    0.07
    etros
    0.06
     Hundred
    0.06
    lemi
    0.06
    TargetException
    0.06
     Norske
    0.06
    alers
    0.06
    haj
    0.06
     عد
    0.06
     Isles
    0.06
    Activations Density 0.005%

    No Known Activations