© 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. 18272
    Prev
    Next
    INDEX
    Explanations

    company, providers, staff, president

    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
    伪
    -0.06
     Travis
    -0.05
     men
    -0.05
    çªĴ
    -0.05
    éħµ
    -0.05
     ÙħÙĤ
    -0.05
    èIJ½
    -0.05
     Fork
    -0.05
     fork
    -0.05
    ä¸ŃæĢ§
    -0.05
    POSITIVE LOGITS
    egna
    0.07
    ç½²
    0.06
    corp
    0.06
     Domen
    0.06
    egram
    0.06
    FromClass
    0.06
    nil
    0.06
    èĤ¡ä¸ľåıĬ
    0.06
    protocol
    0.06
    hap
    0.06
    Activations Density 0.150%

    No Known Activations