© 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. 22571
    Prev
    Next
    INDEX
    Explanations

    medical conditions, types of fuel, or types of substances consumed

    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
    ós
    -0.05
    åĬŁ
    -0.05
    stock
    -0.05
    ·
    -0.05
    iz
    -0.05
    der
    -0.05
    oleh
    -0.05
    æ°
    -0.05
     -
    -0.05
    èį
    -0.05
    POSITIVE LOGITS
    arendra
    0.07
    ILO
    0.06
    éraire
    0.06
    igare
    0.06
    wyż
    0.06
    åĽ°éļ¾åĴĮéĹ®é¢ĺ
    0.06
    ankan
    0.06
    åĬłæĭ¿å¤§
    0.06
    OrFail
    0.06
    urrect
    0.06
    Activations Density 0.023%

    No Known Activations