© 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. 19890
    Prev
    Next
    INDEX
    Explanations

    `code structure identifiers

    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
    engg
    -0.07
    untr
    -0.07
    åĽĽçº§
    -0.07
    ëĭĪëĭ¤
    -0.07
    æŃ¤èµ·
    -0.06
    åĪĨç«Ļ
    -0.06
    .sem
    -0.06
    æĤ¨å°±åı¯ä»¥
    -0.06
    ambi
    -0.06
    าà¸Ħม
    -0.06
    POSITIVE LOGITS
    0.06
    çľĭ
    0.05
     win
    0.05
    åĮħ容
    0.05
    wich
    0.05
    “
    0.05
    op
    0.05
     pr
    0.05
    ue
    0.04
    fty
    0.04
    Activations Density 0.002%

    No Known Activations