© 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. 13787
    Prev
    Next
    INDEX
    Explanations

    numbers, percentages, and estimates

    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
    hya
    -0.07
    ohn
    -0.07
    zend
    -0.07
    eman
    -0.07
    èĢĮéĿŀ
    -0.07
    éľĨ
    -0.07
    zyd
    -0.07
    xcf
    -0.07
    ula
    -0.07
    finder
    -0.07
    POSITIVE LOGITS
    orest
    0.07
    åīįèĢħ
    0.07
    ause
    0.07
    agner
    0.07
    .detach
    0.07
    è´±
    0.07
    igg
    0.06
    åĨ³èĥľ
    0.06
     ranked
    0.06
    éª
    0.06
    Activations Density 0.024%

    No Known Activations