© 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. 18080
    Prev
    Next
    INDEX
    Explanations

    authentic or real

    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
    æĺ¼
    -0.06
    oja
    -0.05
     Bieber
    -0.05
    ical
    -0.05
    /
    -0.05
    -0.05
    oje
    -0.05
    Ù°
    -0.05
    /cgi
    -0.05
    о
    -0.05
    POSITIVE LOGITS
    ä¸įéĢĢ
    0.06
    åIJĪåIJĮæŶ
    0.06
    erce
    0.06
    ä½ĵéªĮåĪ°
    0.06
    adora
    0.06
    /save
    0.06
    ÙĪØ«
    0.06
    modo
    0.06
    AINS
    0.06
    té
    0.05
    Activations Density 0.009%

    No Known Activations