© 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. 21816
    Prev
    Next
    INDEX
    Explanations

    Dalaca, rolling, or iero suffixes

    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
     vibr
    -0.05
    Âł
    -0.05
    è¯·ä½ł
    -0.05
     mon
    -0.05
     layer
    -0.05
    æīįèĥ½
    -0.05
     Phot
    -0.04
    æīįèĥ½å®ŀçİ°
    -0.04
    åij¨åĪ°
    -0.04
     use
    -0.04
    POSITIVE LOGITS
    iero
    0.07
    à¸Ĺà¹īà¸Ńà¸ĩ
    0.06
    új
    0.06
    REEN
    0.06
    éķľ
    0.06
    عÙĦ
    0.06
    atorie
    0.06
    er
    0.06
    dist
    0.06
     alike
    0.06
    Activations Density 0.003%

    No Known Activations