© 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. 20626
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols following text

    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
    ist
    -0.07
    `
    -0.05
     bust
    -0.05
    G
    -0.05
    äºīåıĸ
    -0.05
    åij½
    -0.05
    äºĨä¸Ģåľº
    -0.05
    Bulk
    -0.05
     ust
    -0.05
     vs
    -0.05
    POSITIVE LOGITS
     ("<
    0.07
    skim
    0.07
    ugu
    0.07
    ä¹ĭè¨Ģ
    0.06
    ith
    0.06
    "&
    0.06
     Hins
    0.06
    iski
    0.06
    æīĢåIJij
    0.06
     поÑģÑĤÑĥпи
    0.06
    Activations Density 0.004%

    No Known Activations