© 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. 22152
    Prev
    Next
    INDEX
    Explanations

    python and java code

    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
    -Star
    -0.06
    arith
    -0.06
    ardi
    -0.06
    éĿĪ
    -0.06
    èĤ¥
    -0.06
    ulte
    -0.06
    ugia
    -0.06
    imen
    -0.05
    ugg
    -0.05
    åĬ²
    -0.05
    POSITIVE LOGITS
    ossed
    0.06
    ä½ĵ
    0.05
    prem
    0.05
    اÙģت
    0.05
     preh
    0.05
    aisal
    0.05
     manus
    0.05
    æĢĢéĩĮ
    0.05
     do
    0.05
     infos
    0.05
    Activations Density 0.128%

    No Known Activations