© 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. 45673
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    人åij½
    -0.08
    exion
    -0.08
     moot
    -0.08
    æĮģè¯ģ
    -0.08
     Gabin
    -0.07
    è¿ĶåĽŀé¦ĸ页
    -0.07
    elman
    -0.07
    ļ
    -0.07
    驻马
    -0.07
    okie
    -0.07
    POSITIVE LOGITS
    pe
    0.07
    å¼Ģå§ĭçļĦ
    0.07
    å§ĭãģ¾ãĤĬ
    0.07
     subsequent
    0.07
     ì¶ľë°ľ
    0.07
    -pe
    0.06
    ael
    0.06
    agno
    0.06
    quam
    0.06
     ìĭľìŀij
    0.06
    Activations Density 0.109%

    No Known Activations