© 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. 18064
    Prev
    Next
    INDEX
    Explanations

    without using

    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
     **
    -0.06
    åħħ足
    -0.05
    âĢij
    -0.05
     Fol
    -0.05
     devoir
    -0.05
    溶
    -0.05
    addock
    -0.05
    avat
    -0.05
     Far
    -0.05
    apsed
    -0.05
    POSITIVE LOGITS
    hurst
    0.07
     hereby
    0.06
    ilent
    0.06
     poj
    0.06
     Khanh
    0.06
    jub
    0.06
    yaj
    0.06
    ç½Ĺæĸ¯
    0.06
    letak
    0.06
    ept
    0.06
    Activations Density 0.007%

    No Known Activations