© 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. 10045
    Prev
    Next
    INDEX
    Explanations

    import java

    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
    ise
    -0.07
    rie
    -0.06
    纵使
    -0.06
    pine
    -0.06
     Ùħرج
    -0.06
     .
    -0.06
     {(
    -0.06
    antes
    -0.06
    ographical
    -0.06
    ÑĤ
    -0.06
    POSITIVE LOGITS
    eliz
    0.08
    abler
    0.08
    elier
    0.07
    OnError
    0.07
    urz
    0.07
    cita
    0.07
    agit
    0.07
     ZO
    0.07
    ÙİÙĨÙİÙij
    0.07
    å¼Ĺåħ°
    0.07
    Activations Density 0.006%

    No Known Activations