© 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. 20869
    Prev
    Next
    INDEX
    Explanations

    spending, spending cuts, spending on

    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
    รั
    -0.06
    iner
    -0.06
    als
    -0.06
    ẩn
    -0.05
    bonne
    -0.05
    rips
    -0.05
     Excell
    -0.05
    zinho
    -0.05
    æ¯ıæĹ¥
    -0.05
    ialis
    -0.05
    POSITIVE LOGITS
    aurus
    0.06
    ngo
    0.06
    боле
    0.06
     jazdy
    0.06
    ful
    0.06
    aÄĩ
    0.06
    åıįè¶ħ
    0.05
     mê
    0.05
    onic
    0.05
    żej
    0.05
    Activations Density 0.008%

    No Known Activations