© 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. 2442
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical descriptions

    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
    awan
    -0.08
    ÑĢак
    -0.07
    ulah
    -0.07
     Quar
    -0.07
    èĬ¹
    -0.07
    æ´
    -0.07
    orie
    -0.06
    çĶ¨çģ«
    -0.06
    orer
    -0.06
    alle
    -0.06
    POSITIVE LOGITS
    uten
    0.08
    fy
    0.08
    ensee
    0.07
    shaw
    0.07
    ilig
    0.07
    éĩijå®Ŀ
    0.07
    ledning
    0.07
    ç½ijé¦ĸ页
    0.07
    ISTR
    0.06
    ExceptionHandler
    0.06
    Activations Density 0.002%

    No Known Activations