© 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. 20934
    Prev
    Next
    INDEX
    Explanations

    colons or assignment operators

    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
     unlike
    -0.06
    AMED
    -0.06
    own
    -0.06
    éķ¿å¤§çļĦ
    -0.06
    æ©
    -0.06
    åIJİèĩ³
    -0.06
    odic
    -0.06
    رÙĤÙĬØ©
    -0.05
    åŁł
    -0.05
    anej
    -0.05
    POSITIVE LOGITS
    æĽ´å¥½
    0.07
    charted
    0.05
     better
    0.05
     mas
    0.05
    è´Łéĩį
    0.05
     zeros
    0.05
    éĢIJä¸Ģ
    0.05
    å°ıäºĮ
    0.05
    åĩºçİ°
    0.05
    Ñħождение
    0.05
    Activations Density 0.002%

    No Known Activations