© 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. 21710
    Prev
    Next
    INDEX
    Explanations

    variable

    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
    ä»ĸåij½
    -0.07
    aruh
    -0.07
    鲫
    -0.06
    ÑĢко
    -0.06
    强度é«ĺ
    -0.06
    èµĦæºIJæķ´åIJĪ
    -0.06
    écur
    -0.06
     Ëĩ
    -0.06
    edException
    -0.06
    uncul
    -0.06
    POSITIVE LOGITS
    人åİ»
    0.05
    æį®æѤ
    0.05
     accordingly
    0.05
    osh
    0.05
    ush
    0.05
    ustin
    0.05
    vis
    0.05
    amen
    0.05
    à¹Į
    0.05
     par
    0.05
    Activations Density 0.030%

    No Known Activations