© 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. 18126
    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
    stek
    -0.06
    autorité
    -0.06
    quam
    -0.06
     psycholog
    -0.05
    "People
    -0.05
    ISTER
    -0.05
     hạch
    -0.05
     اÙĦضÙģØ©
    -0.05
    asanya
    -0.05
    ник
    -0.05
    POSITIVE LOGITS
    icke
    0.06
    user
    0.06
     Rath
    0.05
    values
    0.05
    对æĸ¹
    0.05
    åħ±æĮ¯
    0.05
     Ñĥгол
    0.05
    éĢŁ
    0.05
    æĹ¥åĨħ
    0.05
    åķĨ
    0.05
    Activations Density 0.000%

    No Known Activations