© 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. 18806
    Prev
    Next
    INDEX
    Explanations

    setting data in code

    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
    ÙĪبات
    -0.06
    oyer
    -0.06
    acor
    -0.06
    ÏĥÏħ
    -0.06
     overdue
    -0.06
    é¾Ħ
    -0.06
    oft
    -0.05
    æĶ»åĿļ
    -0.05
     symbolic
    -0.05
    oused
    -0.05
    POSITIVE LOGITS
    ogos
    0.06
     Deutsch
    0.06
    èį
    0.05
    пÑĢÑı
    0.05
     Wszyst
    0.05
    客
    0.05
    tel
    0.05
     cứ
    0.05
    armac
    0.05
    æľĢå°ij
    0.05
    Activations Density 0.010%

    No Known Activations