© 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. 20204
    Prev
    Next
    INDEX
    Explanations

    by followed by first name

    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
    人åĿĩåı¯
    -0.06
    à¹Ĥà¸Ľ
    -0.05
    IKE
    -0.05
    Ñĥж
    -0.05
    Ùģر
    -0.05
     nearly
    -0.05
    _SAN
    -0.05
     instruct
    -0.05
    лиÑı
    -0.05
    راس
    -0.05
    POSITIVE LOGITS
    lev
    0.06
    ader
    0.06
    ucer
    0.06
    æijĩ
    0.06
    ersi
    0.06
    å®ī
    0.05
    uc
    0.05
    çª
    0.05
    æĺĮ
    0.05
    äºij
    0.05
    Activations Density 0.001%

    No Known Activations