© 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. 16713
    Prev
    Next
    INDEX
    Explanations

    starts `(`

    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
    inta
    -0.07
    erte
    -0.07
    ycz
    -0.06
    جة
    -0.06
    èle
    -0.06
    è¿ĽäºĨ
    -0.06
     Entspan
    -0.06
    templ
    -0.06
    Ấ
    -0.06
     MeÄiju
    -0.06
    POSITIVE LOGITS
     variation
    0.05
    est
    0.05
    variation
    0.05
    éĻ¤
    0.05
     du
    0.05
     loc
    0.05
    éĻIJ
    0.05
    åľ°ä½į
    0.05
    æĹĹ
    0.05
    款
    0.05
    Activations Density 0.082%

    No Known Activations