© 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. 21940
    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
    ault
    -0.06
    gge
    -0.05
    볨
    -0.05
    dad
    -0.05
    å°ļæľī
    -0.05
    .equal
    -0.05
    bior
    -0.05
    Inh
    -0.05
    upp
    -0.05
    èĭ¥æľī
    -0.05
    POSITIVE LOGITS
    ãģļ
    0.06
    urio
    0.06
    enstein
    0.06
    iid
    0.05
    irse
    0.05
    iar
    0.05
    oriously
    0.05
    åħĥæ°Ķ
    0.05
    ига
    0.05
     اÙĦØ¥Ùģ
    0.05
    Activations Density 0.000%

    No Known Activations