© 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. 20012
    Prev
    Next
    INDEX
    Explanations

    code examples: function, return, $

    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
    odob
    -0.07
     Kraj
    -0.06
    бÑĢа
    -0.06
    juan
    -0.06
    usche
    -0.06
    _____
    -0.06
    ä¸Ģä½ľ
    -0.06
    enu
    -0.06
    brook
    -0.05
    åı¯ä»¥èªªæĺ¯
    -0.05
    POSITIVE LOGITS
    eld
    0.05
    bygg
    0.05
     persistence
    0.05
    èµĦæºIJæķ´åIJĪ
    0.05
    inkan
    0.05
    ars
    0.05
    Ot
    0.05
    gris
    0.05
    æĿĥçĽĬ
    0.05
     remote
    0.05
    Activations Density 0.124%

    No Known Activations