© 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. 46317
    Prev
    Next
    INDEX
    Explanations

    quotes around phrases and terms

    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
    ([$
    -0.08
     ($(
    -0.07
    /Add
    -0.07
    åĬłæĭ¿å¤§
    -0.06
    èĽĭ
    -0.06
    身åĪĨ
    -0.06
    åĽ¾
    -0.06
     ("-
    -0.06
    vs
    -0.06
    (${
    -0.06
    POSITIVE LOGITS
    “
    0.09
    ãĢĮ
    0.09
     “
    0.08
     "
    0.08
    çĦī
    0.08
     «
    0.08
     '
    0.08
    unge
    0.07
    elder
    0.07
    kke
    0.07
    Activations Density 0.160%

    No Known Activations