© 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. 19257
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    Mr
    -0.05
    ola
    -0.05
     flush
    -0.05
    è¿Ļé¦ĸ
    -0.05
    oul
    -0.05
    Õ¼
    -0.05
     plain
    -0.05
     story
    -0.05
    olu
    -0.05
     Mr
    -0.05
    POSITIVE LOGITS
    Occurrences
    0.06
    vegli
    0.06
    ìłķë³´
    0.06
    iard
    0.06
     Wide
    0.06
    Austr
    0.06
    arvi
    0.06
    é«ĺåıij
    0.05
    大é¤IJ
    0.05
     getField
    0.05
    Activations Density 0.078%

    No Known Activations