© 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. 21516
    Prev
    Next
    INDEX
    Explanations

    NOT NULL

    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
    åIJĮæľŁçļĦ
    -0.06
    æł¡
    -0.06
    æŃĩ
    -0.05
    ))[
    -0.05
     investig
    -0.05
    ä¼¼
    -0.05
     rang
    -0.05
    vel
    -0.05
    enda
    -0.05
    оÑĤо
    -0.05
    POSITIVE LOGITS
    anos
    0.06
     lemb
    0.06
     minus
    0.06
    minus
    0.06
    é¹
    0.06
    erat
    0.06
    ãĤĪãĤį
    0.05
    expects
    0.05
    ÑĢд
    0.05
    bove
    0.05
    Activations Density 0.001%

    No Known Activations