© 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. 20574
    Prev
    Next
    INDEX
    Explanations

    state "_pressed", "angular", "System.Windows"

    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
    X
    -0.06
    ir
    -0.05
    èĢ¶
    -0.05
    oute
    -0.05
    鹤
    -0.05
    ï
    -0.05
    æī¬èµ·
    -0.05
    __
    -0.05
    åĺī
    -0.04
    Y
    -0.04
    POSITIVE LOGITS
    tuj
    0.06
     getCategory
    0.06
     znamen
    0.06
    IZZ
    0.06
    åļ¼
    0.06
    REA
    0.06
    emaan
    0.06
    tivo
    0.06
    ÑĤвоÑĢ
    0.06
    anganan
    0.06
    Activations Density 0.001%

    No Known Activations