© 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. 1286
    Prev
    Next
    INDEX
    Explanations

    brush or tool

    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
    åĵģçļĦ
    -0.07
    缩水
    -0.07
    ÑĢемен
    -0.06
    çĥĪ
    -0.06
     scheme
    -0.06
     schemes
    -0.06
     staring
    -0.06
     Arabs
    -0.06
    éĻª
    -0.06
     quota
    -0.05
    POSITIVE LOGITS
    isir
    0.10
    å·¥åħ·
    0.10
    åĩłä¸ĭ
    0.09
    ucho
    0.09
     Meadows
    0.09
    NotFoundError
    0.09
    tui
    0.09
    igl
    0.09
    aida
    0.09
    .tool
    0.09
    Activations Density 0.057%

    No Known Activations