© 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. 21693
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and materials

    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
    idden
    -0.05
    em
    -0.05
    éĢĨ
    -0.05
    еле
    -0.05
    ifer
    -0.05
     Al
    -0.05
    eer
    -0.05
    ÙħÙĨ
    -0.05
    ip
    -0.05
     distinctly
    -0.05
    POSITIVE LOGITS
    louv
    0.06
     confi
    0.06
    æ¸Ĭ
    0.06
    quez
    0.06
    nid
    0.06
     (?,
    0.06
    CIA
    0.06
    LAM
    0.06
    icismo
    0.06
    quier
    0.06
    Activations Density 0.004%

    No Known Activations