© 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. 11270
    Prev
    Next
    INDEX
    Explanations

    timestamps as numbers

    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
    composition
    -0.07
    resa
    -0.07
    Composition
    -0.07
     composition
    -0.07
    alsa
    -0.07
    åıĬ以ä¸ĬçļĦ
    -0.07
    ä¸įä½ı
    -0.06
    ìĥī
    -0.06
     fibres
    -0.06
    xmm
    -0.06
    POSITIVE LOGITS
    ä»»ä½ķåªĴä½ĵ
    0.08
    geo
    0.08
    æŶåĪ»
    0.08
    禧
    0.08
    astia
    0.08
    alde
    0.07
    迪äºļ
    0.07
    çĤ¹å°ı
    0.07
    顺延
    0.07
    otime
    0.07
    Activations Density 0.069%

    No Known Activations