© 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. 17826
    Prev
    Next
    INDEX
    Explanations

    prime minister

    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
    é¢ij
    -0.06
     sk
    -0.06
    åĪĩ
    -0.05
     count
    -0.05
    缮çļĦ
    -0.05
     vis
    -0.05
     spread
    -0.05
    壮大
    -0.05
    J
    -0.05
    iny
    -0.05
    POSITIVE LOGITS
    [:,:
    0.07
    ç¼ĸè¾ijäºİ
    0.07
    ETTA
    0.07
    uger
    0.06
    erro
    0.06
    reek
    0.06
    æĹ¥åĿĩ
    0.06
    olume
    0.06
     akrab
    0.06
    oba
    0.06
    Activations Density 0.015%

    No Known Activations