© 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. 20817
    Prev
    Next
    INDEX
    Explanations

    ancient peoples and their history

    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
    ä¿Ħ
    -0.06
    wann
    -0.05
    æĬ½
    -0.05
    onne
    -0.05
     recover
    -0.05
    auern
    -0.05
    å¦Ĥçģ«å¦Ĥèį¼
    -0.05
    è½°è½°çĥĪ
    -0.05
    uchten
    -0.05
     nue
    -0.05
    POSITIVE LOGITS
    aria
    0.06
     responsibly
    0.06
     implicit
    0.06
     precision
    0.06
    使çĶ¨æŶ
    0.06
    manuel
    0.06
     trom
    0.06
     remarkably
    0.05
     mastery
    0.05
    enuity
    0.05
    Activations Density 0.013%

    No Known Activations