© 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. 18990
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     incluida
    -0.06
    irÃł
    -0.06
     espet
    -0.06
    ichtet
    -0.06
    eyond
    -0.06
    edium
    -0.06
    stra
    -0.06
    utow
    -0.06
     (!((
    -0.06
    echt
    -0.06
    POSITIVE LOGITS
    aire
    0.05
    lite
    0.05
    lu
    0.05
    zc
    0.05
     misc
    0.05
    ogg
    0.05
    个
    0.05
    åľ¨çݰ代
    0.05
    æķij
    0.05
    (
    0.05
    Activations Density 0.000%

    No Known Activations