© 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. 16658
    Prev
    Next
    INDEX
    Explanations

    string checking operations

    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
    -0.08
    æ¬
    -0.06
    andscape
    -0.06
    üe
    -0.06
    siamo
    -0.06
    agon
    -0.06
    enten
    -0.06
    à§įল
    -0.06
    erate
    -0.06
    à¸Ķ
    -0.06
    POSITIVE LOGITS
    versions
    0.06
     versions
    0.06
    æĪĸéĥ¨åĪĨ
    0.06
    arczy
    0.06
    åĥı
    0.05
    çīĪæľ¬
    0.05
     version
    0.05
    gs
    0.05
     intended
    0.05
    çīĪ
    0.05
    Activations Density 0.003%

    No Known Activations