© 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. 62242
    Prev
    Next
    INDEX
    Explanations

    citation 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
    ÙĦÙĪ
    -0.07
    éļĽ
    -0.07
     orally
    -0.07
    ylie
    -0.07
    éħ
    -0.06
    ä¿ĿæĮģé«ĺ度
    -0.06
    äub
    -0.06
    穹
    -0.06
    pair
    -0.06
    bread
    -0.06
    POSITIVE LOGITS
    çľĭä¸į
    0.08
    veis
    0.07
    äºĶå¹´
    0.07
    iến
    0.07
     obliv
    0.07
    dje
    0.07
    ä½¼
    0.07
    åĨį以
    0.07
    tidos
    0.07
    apro
    0.07
    Activations Density 0.021%

    No Known Activations