© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11111
    Prev
    Next
    INDEX
    Explanations

    questions are confusing

    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
    æĽĻ
    -0.08
    documento
    -0.08
    utine
    -0.08
    çªŁ
    -0.08
    orgia
    -0.08
    ึà¹Īà¸ĩ
    -0.08
    áz
    -0.08
    untut
    -0.08
    onar
    -0.07
    _TYP
    -0.07
    POSITIVE LOGITS
     posed
    0.09
     itself
    0.08
    æľ¬èº«
    0.08
    çļĦéĩįçĤ¹
    0.07
     is
    0.07
    æľ¬èº«å°±
    0.07
    çļĦåħ³éĶ®
    0.07
     specifically
    0.06
    çļĦæľ¬è´¨
    0.06
     corpus
    0.06
    Activations Density 0.002%

    No Known Activations