© 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. 29344
    Prev
    Next
    INDEX
    Explanations

    weighted, space, $

    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
    izr
    -0.08
    alay
    -0.07
    ãĥ¼ãĤ¸ãĤ§
    -0.07
    ãĤ¿ãĥ¼ãģ®
    -0.07
     Sâm
    -0.07
    åģĩ
    -0.07
    RR
    -0.07
    .strip
    -0.07
    istus
    -0.06
    ook
    -0.06
    POSITIVE LOGITS
     bil
    0.07
    bil
    0.07
    ank
    0.07
    essel
    0.07
    ":[{"
    0.07
    λÏİ
    0.06
    sob
    0.06
    éĩĮæľī
    0.06
    reens
    0.06
    /storage
    0.06
    Activations Density 0.006%

    No Known Activations