© 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. 16772
    Prev
    Next
    INDEX
    Explanations

    just followed by to, like, as, or in

    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
    åı¯èĥ½ä¼ļæľī
    -0.06
    家æľī
    -0.05
     a
    -0.05
    ngo
    -0.05
    ä¸Ģç§į
    -0.05
    ishly
    -0.05
    rides
    -0.05
    æĢ§éĹ®é¢ĺ
    -0.05
     комплекÑĤе
    -0.05
    级
    -0.05
    POSITIVE LOGITS
    åĪĨ享èĩ³
    0.06
    itações
    0.06
    incia
    0.06
    itação
    0.06
     GRATIS
    0.06
     vanished
    0.06
    ossal
    0.05
    umah
    0.05
    pez
    0.05
    jen
    0.05
    Activations Density 0.065%

    No Known Activations