© 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. 18637
    Prev
    Next
    INDEX
    Explanations

    `(`, `-fold`, `class` (code/markup delimiters) producing specific sequences

    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
    åIJĮæł·
    -0.06
    ên
    -0.06
    ersion
    -0.05
    erce
    -0.05
    мÑĥÑĤ
    -0.05
    peg
    -0.05
    esh
    -0.05
    åħ¬ä¿¡
    -0.05
    ige
    -0.05
    igh
    -0.05
    POSITIVE LOGITS
    ndon
    0.06
    以ä¸ĭ为
    0.06
    çİĩè¾¾
    0.06
    å¹¶ä½ľ
    0.05
     pred
    0.05
     adm
    0.05
     etc
    0.05
    åıĬåIJĦ
    0.05
     decor
    0.05
    èĥģ
    0.05
    Activations Density 0.005%

    No Known Activations