© 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. 21724
    Prev
    Next
    INDEX
    Explanations

    ' and \ in paths

    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
     arc
    -0.05
    ÙĪاÙĨÙĬ
    -0.05
    è¶Ł
    -0.05
    æ²³ä¸Ń
    -0.05
    äºĭä¸Ń
    -0.05
     aux
    -0.05
    4
    -0.05
    罪éŃģ
    -0.05
     loop
    -0.05
    deaux
    -0.05
    POSITIVE LOGITS
    izu
    0.06
    éļİ
    0.06
    jul
    0.06
    èĵĸ
    0.06
    æĿ¾åĬ¨
    0.06
    èĩ¼
    0.06
    ubil
    0.06
    ä¸ĬçŃī
    0.06
    elit
    0.06
    agno
    0.05
    Activations Density 0.001%

    No Known Activations