© 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. 20546
    Prev
    Next
    INDEX
    Explanations

    President Obama

    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
    agnost
    -0.05
     monot
    -0.05
    èĴĻ
    -0.05
     mon
    -0.05
    طار
    -0.05
    ulg
    -0.05
    angg
    -0.05
    매
    -0.05
    umbs
    -0.05
    çĽ£
    -0.05
    POSITIVE LOGITS
    Cb
    0.06
    dach
    0.06
    edos
    0.06
    æĺ¯èĥ½
    0.06
    RAS
    0.06
    curring
    0.06
    麽
    0.05
    aining
    0.05
    iding
    0.05
    zinha
    0.05
    Activations Density 0.369%

    No Known Activations