© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21155
    Prev
    Next
    INDEX
    Explanations

    competition final stages

    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
     final
    -0.06
    æľĢç»Ī
    -0.05
    bras
    -0.05
     chunks
    -0.05
     toÃłn
    -0.05
    éĢIJæŃ¥
    -0.05
     cubes
    -0.05
    åĭ¾
    -0.05
    ê·¼
    -0.05
     từng
    -0.05
    POSITIVE LOGITS
    geschäft
    0.06
    uth
    0.06
    lest
    0.06
    amente
    0.06
    .AI
    0.06
    ector
    0.06
    ÑĢаÑĤоÑĢ
    0.06
    ush
    0.06
    ean
    0.05
    lade
    0.05
    Activations Density 0.002%

    No Known Activations