© 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. 17062
    Prev
    Next
    INDEX
    Explanations

    Mr. or Trini names

    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
     rever
    -0.06
    è¿ĩåĨ¬
    -0.06
    è¿ŀè½½
    -0.06
    ×ķ×ķ
    -0.06
     meanwhile
    -0.06
    ÑīеÑĤ
    -0.06
    away
    -0.06
    ç¬Ķ缴
    -0.06
    arte
    -0.06
    è´¹çĶ¨çĶ±
    -0.06
    POSITIVE LOGITS
     ↵
    0.06
     ellas
    0.05
     prom
    0.05
    iho
    0.05
    ouc
    0.05
    ç©į
    0.05
    еÑĤÑĮ
    0.05
     bes
    0.05
    碱
    0.05
    ни
    0.05
    Activations Density 0.001%

    No Known Activations