© 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. 10450
    Prev
    Next
    INDEX
    Explanations

    modal verbs followed by verbs

    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
    hower
    -0.09
    æķ°æį®çºłéĶĻ
    -0.08
    å·¥ä½ľè¿Ľè¡ĮäºĨ
    -0.08
    žel
    -0.08
    lant
    -0.07
    ãģ£ãģ¡ãĤĥãģĨ
    -0.07
    imuth
    -0.07
    ores
    -0.07
    éria
    -0.07
    åıĸå¾ĹçļĦæĪIJ绩
    -0.07
    POSITIVE LOGITS
     be
    0.07
    /is
    0.07
    âĢ¦âĢ¦ãĢĤ
    0.06
    èĢĮéĤ£äºĽ
    0.06
    çľĭä¸Ĭ
    0.06
     have
    0.06
    rians
    0.06
    nt
    0.06
    æľīä¸Ģ次
    0.06
     effectively
    0.06
    Activations Density 0.133%

    No Known Activations