© 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. 39550
    Prev
    Next
    INDEX
    Explanations

    said object

    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
    ar
    -0.06
    ìłģìĿ¸
    -0.06
    Ïĥει
    -0.06
     the
    -0.06
    arcz
    -0.06
    izin
    -0.06
    ish
    -0.06
    ation
    -0.05
    以ä¸ĭåĩłç§į
    -0.05
     stand
    -0.05
    POSITIVE LOGITS
    eature
    0.09
    same
    0.08
    gados
    0.08
    -END
    0.08
    oned
    0.08
    ôi
    0.08
    DeltaTime
    0.08
    oseb
    0.08
    大亨
    0.08
    wir
    0.08
    Activations Density 0.233%

    No Known Activations