© 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. 21840
    Prev
    Next
    INDEX
    Explanations

    people in professions

    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
    oom
    -0.06
    çĪ·
    -0.06
    æ°´æµĴ
    -0.06
    brechen
    -0.06
     Pequ
    -0.05
    å®¡æł¸åIJİ
    -0.05
    udo
    -0.05
    ÕŃ
    -0.05
    并没
    -0.05
    åĵĪæĭī
    -0.05
    POSITIVE LOGITS
    æŃ¢è·Į
    0.06
     Observer
    0.05
    è¾±
    0.05
    ovin
    0.05
     hovered
    0.05
    sert
    0.05
    ç»ıæµİè¿IJè¡Į
    0.05
    꺼
    0.05
    kson
    0.05
    eded
    0.05
    Activations Density 0.001%

    No Known Activations