© 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. 22875
    Prev
    Next
    INDEX
    Explanations

    numerical codes

    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
    elah
    -0.09
    iore
    -0.08
    اÙĪÙĨ
    -0.08
    å¤ļä¹Ī
    -0.07
    oy
    -0.07
    abase
    -0.07
    -TV
    -0.07
    ç³»
    -0.07
    Ī¬
    -0.07
    ä¸įå°±
    -0.07
    POSITIVE LOGITS
    å¸Ń
    0.08
    wdx
    0.07
     anonymous
    0.07
    åĪ©åīij
    0.07
    ç»ıèIJ¥èĮĥåĽ´åĮħæĭ¬
    0.06
    ÑĬÑı
    0.06
     anonim
    0.06
    çĽĹ
    0.06
    éĢ¢
    0.06
    enders
    0.06
    Activations Density 0.147%

    No Known Activations