© 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. 42623
    Prev
    Next
    INDEX
    Explanations

    python code

    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
    ogi
    -0.07
     asynchronous
    -0.07
    åī¯
    -0.07
    .proto
    -0.07
    æŁ
    -0.07
    éĩĩæł·
    -0.07
    elm
    -0.06
     sampling
    -0.06
    iod
    -0.06
    å¼ĤæŃ¥
    -0.06
    POSITIVE LOGITS
    ewan
    0.08
     cál
    0.07
    quisite
    0.07
     Geme
    0.07
    æİĮä¸Ĭ
    0.07
    çĤ¹è¿ĻéĩĮ
    0.07
    aide
    0.07
    aider
    0.07
    bere
    0.07
    letcher
    0.07
    Activations Density 0.006%

    No Known Activations