© 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. 12087
    Prev
    Next
    INDEX
    Explanations

    titles and references

    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
    pia
    -0.08
    aner
    -0.07
    éĵ¿
    -0.07
    alina
    -0.07
    erop
    -0.06
    å°¼äºļ
    -0.06
    aed
    -0.06
    éron
    -0.06
    holt
    -0.06
    amid
    -0.06
    POSITIVE LOGITS
    æĮĩçļĦæĺ¯
    0.09
     referring
    0.08
     [
    0.08
    æĮĩ
    0.08
    ï¼Ī
    0.07
    åį³ä»¥
    0.07
    —the
    0.07
    /us
    0.07
    å°±æĺ¯æĮĩ
    0.07
    æīĢæĮĩ
    0.07
    Activations Density 0.086%

    No Known Activations