© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20688
    Prev
    Next
    INDEX
    Explanations

    review articles

    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
     suite
    -0.06
    langs
    -0.06
     rehe
    -0.06
    icat
    -0.06
    رج
    -0.05
    شار
    -0.05
     ready
    -0.05
    CID
    -0.05
     matters
    -0.05
    .mid
    -0.05
    POSITIVE LOGITS
     poll
    0.06
    ä¸īéĿ¢
    0.06
    å°ģéĹŃå¼ı
    0.06
    çe
    0.05
    poll
    0.05
     fen
    0.05
    anza
    0.05
     enclosed
    0.05
    éĦ
    0.05
     mor
    0.05
    Activations Density 0.002%

    No Known Activations