© 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. 16831
    Prev
    Next
    INDEX
    Explanations

    alp happened

    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
    éĩįè¦ģäºĨ
    -0.05
    +_
    -0.05
    äºĭäºĨ
    -0.05
    creens
    -0.05
    iform
    -0.05
    еÑĤÑĮ
    -0.05
    ,port
    -0.05
    orado
    -0.05
    departure
    -0.05
    ãĤ¹ãĤŃ
    -0.05
    POSITIVE LOGITS
     sout
    0.06
    Âł
    0.05
    èĵ¬
    0.05
    upu
    0.05
    æĮ½
    0.05
    Ŀ
    0.05
     independently
    0.05
     souten
    0.05
     dấu
    0.05
    orce
    0.05
    Activations Density 0.002%

    No Known Activations