© 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. 19251
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    zni
    -0.06
    é»ĺ
    -0.06
    ).-
    -0.06
    rena
    -0.06
    eram
    -0.06
    encontre
    -0.06
    >ID
    -0.06
    zana
    -0.06
    ç¥ŀå±±
    -0.06
    onge
    -0.06
    POSITIVE LOGITS
    _
    0.05
     titular
    0.05
     dear
    0.05
    Ñīи
    0.05
    ental
    0.05
    ject
    0.05
    è¿Ļä¸Ģ
    0.05
    äºĨè¿Ļä¸Ģ
    0.05
     [](
    0.05
     má»±c
    0.05
    Activations Density 0.000%

    No Known Activations