© 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. 17385
    Prev
    Next
    INDEX
    Explanations

    "am" followed by a verb or adjective

    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
    доваÑĤÑĮ
    -0.07
    ×ŀף
    -0.07
     undes
    -0.07
    æŃ¤é¡¹
    -0.06
    ä¸įæĸĻ
    -0.06
     spur
    -0.06
    åī§çĥĪçļĦ
    -0.06
    Äĥn
    -0.06
    heits
    -0.06
    ikhail
    -0.06
    POSITIVE LOGITS
    ä¹IJ天
    0.07
    æīĵæİī
    0.07
    éħ¸åĮĸ
    0.07
    ÎŃÏģα
    0.07
    Drop
    0.07
     zust
    0.07
    çľĭä¸ĭ
    0.07
    ä¼Ļ
    0.07
    æĬ½ç©º
    0.07
    _drop
    0.06
    Activations Density 0.002%

    No Known Activations