© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21458
    Prev
    Next
    INDEX
    Explanations

    Richard L. Thornburgh, U. S. Atty

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åĪĨ享
    -0.06
     del
    -0.05
     perv
    -0.05
    好èĩªå·±çļĦ
    -0.05
    åıªèĥ½åľ¨
    -0.05
    åıªèĥ½æĺ¯
    -0.04
    -0.04
    H
    -0.04
    对èĩªå·±
    -0.04
    åıĺæĢģ
    -0.04
    POSITIVE LOGITS
    olos
    0.07
    abella
    0.07
     dust
    0.07
    ÙĪÛĮÛĮ
    0.06
    åĪĨ许
    0.06
    iola
    0.06
    __*/
    0.06
    ves
    0.06
    afür
    0.06
    centes
    0.06
    Activations Density 0.001%

    No Known Activations