© 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. 22122
    Prev
    Next
    INDEX
    Explanations

    for example

    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
    å¦ĤæѤ
    -0.06
    org
    -0.06
    ave
    -0.06
    为ä¸Ģ个
    -0.06
    üst
    -0.05
    ↵↵    ↵
    -0.05
     Whether
    -0.05
    ouse
    -0.05
    ↵   ↵
    -0.05
    为ä¹ĭ
    -0.05
    POSITIVE LOGITS
    lessly
    0.06
    angeb
    0.06
    çĽ¸ä¿¡å¤§å®¶
    0.06
    killer
    0.06
    åIJĦåı¸
    0.05
    anu
    0.05
    egner
    0.05
    åĬłæĭ¿å¤§
    0.05
    ä»ĭç»į说
    0.05
    erder
    0.05
    Activations Density 0.019%

    No Known Activations