© 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. 11508
    Prev
    Next
    INDEX
    Explanations

    reported that

    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
     _______,
    -0.11
    ãģ£ãģ¦ãģĬãĤĬ
    -0.10
     обаÑĩе
    -0.09
    (""),
    -0.09
     "/",
    -0.09
     ìŀĪìĹĪëĬĶëį°
    -0.09
    ãģĹãģ¦ãģĬãĤĬ
    -0.09
     ê°ĢëĬ¥íķĺë©°
    -0.09
     zwar
    -0.09
    ãģĮãģĤãĤĬ
    -0.08
    POSITIVE LOGITS
     appunto
    0.10
    ä¹Łä¸įä¾ĭå¤ĸ
    0.09
    **ãĢĤ
    0.09
     accordingly
    0.08
    åIJİèĢħ
    0.08
    ++.
    0.08
    )ãĢĤ
    0.08
     therein
    0.08
    ï½ŀãĢĤ
    0.07
    )."
    0.07
    Activations Density 1.936%

    No Known Activations