© 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. 21668
    Prev
    Next
    INDEX
    Explanations

    high-level language

    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
    lanjut
    -0.06
    lili
    -0.06
    gefähr
    -0.06
    utzt
    -0.06
    porte
    -0.06
    veille
    -0.06
     molec
    -0.06
    ument
    -0.06
    家åºĹ
    -0.06
    коли
    -0.06
    POSITIVE LOGITS
    缴æİ¥
    0.06
     directly
    0.05
     langsung
    0.05
    el
    0.05
     Freed
    0.05
    immel
    0.05
    wi
    0.05
    ç¶
    0.05
    cs
    0.05
    U
    0.05
    Activations Density 0.003%

    No Known Activations