© 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. 32364
    Prev
    Next
    INDEX
    Explanations

    mortgage debt or holders

    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
    -0.09
    çĴĭ
    -0.08
    äºļçī¹
    -0.08
    دÙĪز
    -0.08
    ofilm
    -0.08
    bies
    -0.08
    heten
    -0.08
    ÃĶI
    -0.08
     assemb
    -0.08
    olet
    -0.08
    POSITIVE LOGITS
    è¯į
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    ors
    0.07
    æłĵ
    0.07
    çī©ä»¶
    0.07
    åħ¸å½ĵ
    0.07
    åı¥è¯Ŀ说
    0.07
    aged
    0.07
    è©ŀ
    0.07
    æľīæķĪæľŁåĨħ
    0.07
    Activations Density 0.007%

    No Known Activations