© 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. 19812
    Prev
    Next
    INDEX
    Explanations

    err != nil

    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
     деле
    -0.06
    ])**
    -0.05
    bourg
    -0.05
    ests
    -0.05
    çļĦåħ¨
    -0.05
    imdi
    -0.05
    ylim
    -0.05
    æ°ij
    -0.05
    ÑģÑĤÑĮÑİ
    -0.05
    estu
    -0.05
    POSITIVE LOGITS
    umi
    0.05
    istol
    0.05
     mall
    0.05
    TOR
    0.05
    Ãłn
    0.05
    rific
    0.05
     cri
    0.05
    LT
    0.05
     Associated
    0.05
    Associated
    0.05
    Activations Density 0.003%

    No Known Activations