© 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. 21121
    Prev
    Next
    INDEX
    Explanations

    examples like e.g

    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
    åĢ
    -0.06
    hp
    -0.06
    ä½Ļ
    -0.05
    iven
    -0.05
    S
    -0.05
     доÑĢо
    -0.05
    led
    -0.04
    Ïĥί
    -0.04
    ä¸ĭä¸Ģç§Ĵ
    -0.04
    à¹Ģหลืà¸Ń
    -0.04
    POSITIVE LOGITS
    esprit
    0.07
    ä»Ķ
    0.07
     Terlebih
    0.06
    kons
    0.06
    æľīæĿ¡
    0.06
     Sayangnya
    0.06
    enfants
    0.06
    ضاء
    0.06
    iná
    0.06
    maks
    0.06
    Activations Density 0.001%

    No Known Activations