© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38380
    Prev
    Next
    INDEX
    Explanations

    corrupt unscrambling noisy packed generated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    족
    -0.08
    lider
    -0.08
    éŀį
    -0.08
    åıĬ对
    -0.07
     ÑĥлÑĮÑĤ
    -0.07
    ffin
    -0.07
    yntax
    -0.07
    ultos
    -0.07
    大ä¼ļåłĤ
    -0.07
     Lec
    -0.07
    POSITIVE LOGITS
     corrupt
    0.08
     clues
    0.08
    æķħæĦı
    0.08
     unknown
    0.08
    失äºĨ
    0.08
    éģĹ失
    0.08
    è¿·ç³Ĭ
    0.08
     неизвеÑģÑĤ
    0.08
     clue
    0.08
    ç¼Ń
    0.07
    Activations Density 0.055%

    No Known Activations