© 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. 21294
    Prev
    Next
    INDEX
    Explanations

    meeting people

    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
     Ahead
    -0.06
    ç§
    -0.06
    zug
    -0.06
     preload
    -0.06
    еÑĤÑĢо
    -0.05
    chat
    -0.05
    w
    -0.05
    çݰ代
    -0.05
    é¢ĦåħĪ
    -0.05
    rad
    -0.05
    POSITIVE LOGITS
    ató
    0.07
    ione
    0.07
    Ùģع
    0.06
    PageIndex
    0.06
    è·Įå®ķèµ·ä¼ı
    0.05
    ysz
    0.05
    ä¸Ģè·ĥ
    0.05
    éľĦ
    0.05
     breakout
    0.05
    央
    0.05
    Activations Density 0.020%

    No Known Activations