© 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. 19811
    Prev
    Next
    INDEX
    Explanations

    EditText or RECORD

    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
    -0.06
    ç²¾åĩĨ
    -0.05
    ĩ
    -0.05
    å¯Ľ
    -0.05
     autos
    -0.05
    ä¼ij
    -0.05
     Re
    -0.05
     Common
    -0.05
     Auto
    -0.05
    ersh
    -0.05
    POSITIVE LOGITS
    à¹īà¸Ńà¸ĩ
    0.06
    inkel
    0.06
    imoni
    0.06
    éĻ
    0.06
    istant
    0.06
     rectific
    0.06
    [âĢ¦
    0.06
    akang
    0.06
    ensk
    0.06
    éĻĮ
    0.06
    Activations Density 0.006%

    No Known Activations