© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16717
    Prev
    Next
    INDEX
    Explanations

    roman to int, morse code, doctype html

    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
    Negative Logits
    è¡Į
    -0.05
    è¡Įæķ°
    -0.05
    ä¸ĢåĪĩ
    -0.05
    tha
    -0.05
    éĢıå½»
    -0.05
    à¹īà¸Ļ
    -0.05
    åºĶå°½
    -0.04
     wink
    -0.04
    ASH
    -0.04
     μÎŃÏĥα
    -0.04
    POSITIVE LOGITS
    ç«ł
    0.06
    illas
    0.06
     Lifetime
    0.06
     замÑĭ
    0.06
    謹æħİ
    0.06
    **–
    0.06
    gether
    0.06
    èħĬèĤī
    0.06
    çĻ¾å²ģ
    0.06
     viag
    0.06
    Activations Density 0.003%

    No Known Activations