© 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. 21032
    Prev
    Next
    INDEX
    Explanations

    isolate, improve, independent, limited, compromise

    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
    åĬ¡
    -0.06
    ahari
    -0.06
    림
    -0.06
    eware
    -0.05
    esor
    -0.05
     ocas
    -0.05
    å°±ä¸ļå½¢åĬ¿
    -0.05
    oyal
    -0.05
    law
    -0.05
    aware
    -0.05
    POSITIVE LOGITS
     worst
    0.07
     격
    0.07
    è´¥
    0.06
    éļĶ离
    0.06
     progress
    0.06
    åĿı
    0.06
    tap
    0.06
    artment
    0.06
    æįŁ
    0.06
    umed
    0.06
    Activations Density 0.034%

    No Known Activations