© 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. 19097
    Prev
    Next
    INDEX
    Explanations

    United States or similar endings

    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
    jaz
    -0.06
    اÙĩÛĮ
    -0.06
    agan
    -0.06
    forgettable
    -0.06
    awai
    -0.06
    engel
    -0.06
    verband
    -0.05
    صÙĦ
    -0.05
    åıijçİ°åľ¨
    -0.05
    ERI
    -0.05
    POSITIVE LOGITS
    好
    0.06
    vice
    0.05
     vice
    0.05
    å¿ħè¦ģæŶ
    0.05
    iete
    0.05
    itte
    0.05
     running
    0.05
    ied
    0.05
    undance
    0.05
    åĢĴ
    0.05
    Activations Density 0.004%

    No Known Activations