© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18737
    Prev
    Next
    INDEX
    Explanations

    arithmetic and numbers

    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
    2
    -0.07
    (
    -0.06
    1
    -0.06
    оÑģÑĮ
    -0.06
    3
    -0.06
    most
    -0.05
    T
    -0.05
    R
    -0.05
    .g
    -0.05
     (
    -0.05
    POSITIVE LOGITS
    spre
    0.08
    denken
    0.07
    êµīìŀ¥
    0.07
    lieben
    0.07
    èįŁ
    0.07
    schau
    0.07
    تز
    0.07
    꽤
    0.07
    quilibrio
    0.06
    engin
    0.06
    Activations Density 0.031%

    No Known Activations