© 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. 22041
    Prev
    Next
    INDEX
    Explanations

    identification numbers

    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
    OOM
    -0.07
    بÙĬÙĩ
    -0.07
    åıĪæĬĬ
    -0.07
    åĨįæĬĬ
    -0.06
    oom
    -0.06
    éĢĥ
    -0.06
    GIO
    -0.06
    çŀ»
    -0.06
    cole
    -0.06
    æĽ
    -0.06
    POSITIVE LOGITS
    alink
    0.07
     subscribed
    0.07
    rott
    0.07
     Erst
    0.07
    éĿŀ常ä¸įéĶĻ
    0.06
    gues
    0.06
    OrFail
    0.06
    ÃŃr
    0.06
    brook
    0.06
    ร
    0.06
    Activations Density 0.001%

    No Known Activations