© 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. 57116
    Prev
    Next
    INDEX
    Explanations

    can be

    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
    odos
    -0.08
     ìķĦëĭĮê°Ģ
    -0.07
    å°¼å°Ķ
    -0.07
    setattr
    -0.07
    bris
    -0.07
    odo
    -0.07
    acto
    -0.06
    ÏĦÏģÏĮ
    -0.06
    aper
    -0.06
    resenter
    -0.06
    POSITIVE LOGITS
     optionally
    0.09
    ’t
    0.08
     feas
    0.08
     jederzeit
    0.08
    以任ä½ķ
    0.07
     safely
    0.07
     Optionally
    0.07
    å¤ļè¾¾
    0.07
    éļ¨æĻĤ
    0.07
     potentially
    0.07
    Activations Density 0.526%

    No Known Activations