© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18460
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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
    /Set
    -0.05
    عة
    -0.05
    ξι
    -0.04
    ä¸Ģè§Ī
    -0.04
    rar
    -0.04
    å°ıåı·
    -0.04
     Show
    -0.04
    érie
    -0.04
    utin
    -0.04
    robe
    -0.04
    POSITIVE LOGITS
    anni
    0.06
    orious
    0.06
    ughty
    0.06
    wasser
    0.06
    山寨
    0.06
    ä¸ĸçķĮ第ä¸Ģ
    0.06
     Himself
    0.06
    uras
    0.06
    ä»»ä½ķä¸ľè¥¿
    0.06
    ulet
    0.05
    Activations Density 0.062%

    No Known Activations