© 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. 21192
    Prev
    Next
    INDEX
    Explanations

    diesel engine components

    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
    itol
    -0.06
    orer
    -0.06
     اÙĦعÙĦÙĬا
    -0.06
    婧
    -0.06
    éĩijæľį
    -0.06
    opper
    -0.06
     Santo
    -0.06
    طب
    -0.06
     عÙĦ
    -0.06
    andle
    -0.05
    POSITIVE LOGITS
    æł·åŃIJ
    0.06
     harsh
    0.05
    zü
    0.05
    éĻ°
    0.05
    Ñģо
    0.05
     presence
    0.05
    mog
    0.05
    裤
    0.05
    Ò£
    0.05
    azzi
    0.05
    Activations Density 0.006%

    No Known Activations