© 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. 22492
    Prev
    Next
    INDEX
    Explanations

    hydroxy-

    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
    ispens
    -0.07
    ehrte
    -0.06
    iors
    -0.06
    Kamis
    -0.06
     лиÑĨом
    -0.06
    gart
    -0.06
    è´°
    -0.06
    GMT
    -0.06
     normalt
    -0.06
    bardziej
    -0.06
    POSITIVE LOGITS
     Fi
    0.07
    é¢ĺ
    0.05
    -Fi
    0.05
    pra
    0.05
     overall
    0.05
    pr
    0.05
    éĮ
    0.05
    ä¸Ģèµ·
    0.05
    utin
    0.05
    åĶĩ
    0.05
    Activations Density 0.004%

    No Known Activations