© 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. 48145
    Prev
    Next
    INDEX
    Explanations

    reflect permanently?

    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
    asilan
    -0.08
    æł¼å°Ķ
    -0.08
    gek
    -0.08
    daq
    -0.08
    ntax
    -0.08
    ftime
    -0.08
     dikat
    -0.08
     rakel
    -0.08
    à¹ģà¸ģà¹Ī
    -0.08
    új
    -0.08
    POSITIVE LOGITS
     somehow
    0.15
    æŁIJç§į
    0.13
    æŁIJäºĽ
    0.12
    åľ¨æŁIJäºĽ
    0.10
     irgendwie
    0.09
     certain
    0.09
     maybe
    0.09
    æŁIJç§įæĦıä¹īä¸Ĭ
    0.09
     alguna
    0.08
    æŁIJ个
    0.08
    Activations Density 0.039%

    No Known Activations