© 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. 17046
    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
    Invariant
    -0.06
    ấc
    -0.06
    åİ¥
    -0.06
     invariant
    -0.06
    åİŁåĽłæĺ¯
    -0.06
    äºĨ
    -0.05
    æł¼
    -0.05
    atk
    -0.05
    ıyla
    -0.05
     yourselves
    -0.05
    POSITIVE LOGITS
    ancy
    0.07
    em
    0.06
     nub
    0.06
    itores
    0.06
    heng
    0.06
    ez
    0.06
    éļĨéĩį
    0.06
    queta
    0.06
    rozum
    0.05
    SelectionMode
    0.05
    Activations Density 0.000%

    No Known Activations