© 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. 22557
    Prev
    Next
    INDEX
    Explanations

    understanding of

    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
    ês
    -0.06
     understanding
    -0.06
    ments
    -0.05
    大åĪ©
    -0.05
    esses
    -0.05
    ç®Ĺæĺ¯
    -0.05
    è¶ģ
    -0.05
     versteht
    -0.05
    utherland
    -0.05
    tes
    -0.05
    POSITIVE LOGITS
    iously
    0.06
    fall
    0.06
     маÑģÑģив
    0.06
    аÑģÑģив
    0.06
    wegen
    0.06
    vide
    0.06
    ÑģмоÑĤÑĢиÑĤе
    0.06
    ickers
    0.06
    addons
    0.06
    宫å¤ĸ
    0.06
    Activations Density 0.012%

    No Known Activations