© 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. 17460
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by closing parentheses

    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
    erts
    -0.06
    alsy
    -0.05
    éºĵ
    -0.05
    idler
    -0.05
    erset
    -0.05
    为é¦ĸ
    -0.05
    çĶŁåīį
    -0.05
    Ø°Ùģ
    -0.05
    leine
    -0.05
     seiz
    -0.05
    POSITIVE LOGITS
    mb
    0.06
    ule
    0.06
    tian
    0.06
    认è¯ĨäºĨ
    0.05
     Georgetown
    0.05
    OOD
    0.05
    inger
    0.05
    illo
    0.05
    issan
    0.05
    ileged
    0.05
    Activations Density 0.119%

    No Known Activations