© 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. 22472
    Prev
    Next
    INDEX
    Explanations

    also introduces additional information

    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
    er
    -0.07
    -0.06
     (
    -0.06
    ä¼ļ
    -0.06
    aped
    -0.06
    istic
    -0.06
    ly
    -0.05
    ium
    -0.05
     to
    -0.05
    ed
    -0.05
    POSITIVE LOGITS
    ulp
    0.07
    vara
    0.06
    à¸Ńยูà¹Īà¸Ń
    0.06
    åħ¶èģĮ
    0.06
     tinggal
    0.06
    anka
    0.06
    ìĺĢëįĺ
    0.06
    imana
    0.06
    ãģĭãĤīãģĵãģĿ
    0.06
    åĵī
    0.06
    Activations Density 0.011%

    No Known Activations