© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15902
    Prev
    Next
    INDEX
    Explanations

    rock drills or thermal risks

    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
    rod
    -0.08
    鼷
    -0.07
    vs
    -0.06
    浩
    -0.06
     bur
    -0.06
    wt
    -0.06
     slot
    -0.06
    cl
    -0.06
    ÅĤaw
    -0.06
    ray
    -0.06
    POSITIVE LOGITS
    åĪĨåĪ¥æĺ¯
    0.09
    linky
    0.08
    å°¼æĸ¯
    0.08
    åĪ©çī©
    0.08
    åĪĨåĪ¥
    0.08
    åĪĨåĪ«ä¸º
    0.08
    éĩijé¦Ļ
    0.08
    μμα
    0.08
    taat
    0.08
    κια
    0.08
    Activations Density 0.362%

    No Known Activations