© 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. 50323
    Prev
    Next
    INDEX
    Explanations

    Mirror, mirrored, ghosts, Schwarz, extension

    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
    èŃ²
    -0.08
    æĶ
    -0.07
     convertible
    -0.07
    popular
    -0.07
    忧
    -0.07
    ubu
    -0.07
     Rau
    -0.06
    aime
    -0.06
    åı£åijĨ
    -0.06
     paren
    -0.06
    POSITIVE LOGITS
    éķľåĥı
    0.12
    åĢĴå½±
    0.11
    Mirror
    0.11
    mirror
    0.10
    _mirror
    0.10
     mirror
    0.10
     mirrored
    0.09
    éķľ
    0.09
     Mirror
    0.09
    éķľéĿ¢
    0.09
    Activations Density 0.001%

    No Known Activations