© 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. 50642
    Prev
    Next
    INDEX
    Explanations

    section headers like "Field" or "Introduction"

    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
    empo
    -0.08
    elat
    -0.08
    anser
    -0.08
    dito
    -0.08
    icode
    -0.08
    elper
    -0.08
    asiat
    -0.08
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.08
    anoia
    -0.07
    laget
    -0.07
    POSITIVE LOGITS
    é¦ĸåħĪéľĢè¦ģ
    0.09
    åĩ¡æľ¬ç½ij注æĺİ
    0.09
    é¦ĸåħĪ
    0.08
     먼ìłĢ
    0.08
    åħĪä»İ
    0.08
    ÑĥÑħ
    0.08
    åħĪçľĭ
    0.08
     First
    0.08
    åħĪå°Ĩ
    0.07
     firstly
    0.07
    Activations Density 0.135%

    No Known Activations