© 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. 16697
    Prev
    Next
    INDEX
    Explanations

    Trini, Jemaine, SEK, ch, Ob, st

    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
    kena
    -0.08
    eldes
    -0.07
    å¾ģ
    -0.06
    ozn
    -0.06
    اÙĨØ©
    -0.06
    å¹¿æ³Ľå¼Ģå±ķ
    -0.06
    egue
    -0.06
     beneficiation
    -0.06
    heu
    -0.06
     terci
    -0.06
    POSITIVE LOGITS
    èIJ½
    0.06
    åĩºå¥ĩ
    0.06
     d
    0.05
     u
    0.05
    ä¸ĸ纪åĪĿ
    0.05
     fall
    0.05
    0.05
    ä¸įå°½
    0.05
     Falle
    0.05
    jä
    0.05
    Activations Density 0.004%

    No Known Activations