© 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. 18712
    Prev
    Next
    INDEX
    Explanations

    geographic coordinates or numeric data

    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
    mah
    -0.05
    imus
    -0.05
    urat
    -0.05
    гий
    -0.05
     sign
    -0.05
    à¸Ľà¸±à¹īà¸Ļ
    -0.05
    羣çļĦè¦ģ
    -0.05
     personally
    -0.05
    ä¸įèĥ½ä½ľä¸º
    -0.05
    ig
    -0.05
    POSITIVE LOGITS
    ewhat
    0.06
    êne
    0.06
    åŁºæľ¬ä¸Ĭæĺ¯
    0.06
    åĹľ
    0.06
     råd
    0.06
    è¿ĻçŃī
    0.06
    opr
    0.06
     piè
    0.06
    èħ
    0.06
    Anywhere
    0.06
    Activations Density 0.003%

    No Known Activations