© 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. 41853
    Prev
    Next
    INDEX
    Explanations

    classification of places and entities

    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
    ...).
    -0.08
    ��
    -0.08
     ↵    ↵
    -0.08
    ...",
    -0.07
    -
    -0.07
    ab
    -0.07
    ���
    -0.07
    âĢ¦âĢ¦ãĢĤ
    -0.07
    .).
    -0.07
     ↵↵↵↵↵
    -0.07
    POSITIVE LOGITS
    Äħtek
    0.10
    lå
    0.09
    /GPL
    0.09
    ityEngine
    0.09
    ↵
    0.08
    ÅĻe
    0.08
    nTo
    0.08
    oref
    0.08
    klink
    0.08
    æīĢå±ŀåĪĨç±»
    0.08
    Activations Density 0.417%

    No Known Activations