© 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. 17389
    Prev
    Next
    INDEX
    Explanations

    names, descriptions, or states of being

    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
    สัà¸ĩà¸ģัà¸Ķ
    -0.07
    ÑĢиÑģÑĤи
    -0.07
    ê»ı
    -0.06
     momentan
    -0.06
     mắt
    -0.06
    now
    -0.06
    eller
    -0.06
    æīĢ以çİ°åľ¨
    -0.06
    no
    -0.06
    ло
    -0.06
    POSITIVE LOGITS
     nhau
    0.07
    uhan
    0.06
     pés
    0.06
    模
    0.05
    gro
    0.05
    رب
    0.05
    bourne
    0.05
    obe
    0.05
    纯粹
    0.05
    éĻĮçĶŁ
    0.05
    Activations Density 0.001%

    No Known Activations