© 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. 34456
    Prev
    Next
    INDEX
    Explanations

    journal citations and technical jargon

    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
    èĢĮéĻį
    -0.07
    -indent
    -0.07
    ç§įçļĦ
    -0.07
    egger
    -0.07
    jure
    -0.07
    çī¹å°Ķ
    -0.07
    onders
    -0.07
    çĪ±æĥľ
    -0.07
    -manager
    -0.06
    sii
    -0.06
    POSITIVE LOGITS
    ovich
    0.08
    ATOM
    0.07
    é«ĺ度çļĦ
    0.07
    gles
    0.06
     frozen
    0.06
    GOP
    0.06
    ajo
    0.06
     outgoing
    0.06
     Photon
    0.06
    ytu
    0.06
    Activations Density 0.001%

    No Known Activations