© 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. 49636
    Prev
    Next
    INDEX
    Explanations

    question marks or unspecified characters

    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
    obao
    -0.08
    egger
    -0.07
    anza
    -0.07
    anford
    -0.07
    -generic
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    åı²
    -0.07
    .Keyboard
    -0.07
    ä»ģæħĪ
    -0.07
    çļĦ人éĥ½
    -0.07
    POSITIVE LOGITS
    æĬij
    0.07
    rather
    0.07
    illet
    0.06
    æĬijæĪĸ
    0.06
    VS
    0.06
    unicode
    0.06
     Prak
    0.06
    imah
    0.06
    upil
    0.06
    brig
    0.06
    Activations Density 0.010%

    No Known Activations