© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20261
    Prev
    Next
    INDEX
    Explanations

    Egypt and Egyptian

    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
    oidal
    -0.06
    ubs
    -0.06
    åĪ¶éĢłæľīéĻIJåħ¬åı¸
    -0.06
    ezu
    -0.06
    laces
    -0.06
    aved
    -0.06
    ä¸įåĢ¦
    -0.06
    fällig
    -0.06
    åݦ
    -0.06
    berry
    -0.06
    POSITIVE LOGITS
    gypt
    0.08
     Egypt
    0.07
    Egypt
    0.07
    åŁĥåıĬ
    0.06
     Egyptian
    0.05
    apyrus
    0.05
    python
    0.05
    ysis
    0.05
    posit
    0.05
    .python
    0.05
    Activations Density 0.011%

    No Known Activations