© 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. 51434
    Prev
    Next
    INDEX
    Explanations

    file extensions and paths

    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
    abt
    -0.09
    åºĥåijĬãģ¯
    -0.09
    blr
    -0.08
    amn
    -0.08
    æľºæŀĦåĴĮ
    -0.07
    çļĦä¸Ģ件äºĭ
    -0.07
    amá
    -0.07
    ksam
    -0.07
    estero
    -0.07
    udas
    -0.07
    POSITIVE LOGITS
    /--
    0.08
    /,
    0.07
    iston
    0.07
    aho
    0.07
    /'
    0.07
    /-
    0.07
    ÑĤей
    0.06
    缸è¾ħ缸æĪIJ
    0.06
    ennen
    0.06
    ä¸įçł´
    0.06
    Activations Density 0.264%

    No Known Activations