© 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. 18376
    Prev
    Next
    INDEX
    Explanations

    nuclear weapon, option, arsenal, deal, submarine, energy, plant

    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
    uos
    -0.07
    ington
    -0.07
     increÃŃ
    -0.07
    ional
    -0.07
    æ¯ĶåĪ©
    -0.06
    uada
    -0.06
    ocracy
    -0.06
    деÑĢжка
    -0.06
    vÃŃo
    -0.06
    ลาย
    -0.06
    POSITIVE LOGITS
    ÙģاÙģ
    0.05
    a
    0.05
    åĴĮæ°Ķ
    0.05
     boss
    0.05
     веÑī
    0.05
    ا
    0.05
    æľīä½į
    0.05
    autical
    0.04
    å¤ĸçļĦ
    0.04
    éģİçļĦ
    0.04
    Activations Density 0.006%

    No Known Activations