© 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. 20278
    Prev
    Next
    INDEX
    Explanations

    GNU General Public License

    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
    fel
    -0.06
     palma
    -0.06
    ↵                        ↵
    -0.06
    åľ°éĹ®éģĵ
    -0.06
    ook
    -0.06
    pace
    -0.05
    orama
    -0.05
    æľ¬çľģ
    -0.05
    roc
    -0.05
    bid
    -0.05
    POSITIVE LOGITS
     гаÑĢмони
    0.06
    ãģĦãĤĭ
    0.06
    éné
    0.05
    cardo
    0.05
    人士
    0.05
    heureusement
    0.05
    gré
    0.05
    лÑİ
    0.05
    建æĪIJ
    0.05
    еÑĢов
    0.05
    Activations Density 0.018%

    No Known Activations