© 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. 21948
    Prev
    Next
    INDEX
    Explanations

    groups of people

    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
    uddy
    -0.07
    udge
    -0.06
    alni
    -0.06
    yna
    -0.06
    ciar
    -0.06
    vaard
    -0.06
    缴æİ¥æĪĸ
    -0.06
    åħļæĢ»æĶ¯ä¹¦è®°
    -0.06
    é¢ĦéĢīèµĽ
    -0.06
    ัว
    -0.06
    POSITIVE LOGITS
    å¾Ģ
    0.05
    åijĺå·¥
    0.05
     its
    0.05
    éĻ¢åĨħ
    0.05
     coverage
    0.05
     life
    0.05
    å»Ĭ
    0.05
     living
    0.05
    延
    0.05
    éķ¿çŁŃ
    0.05
    Activations Density 0.077%

    No Known Activations