© 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. 17185
    Prev
    Next
    INDEX
    Explanations

    Legal citations 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
    ulo
    -0.07
    å»ī
    -0.07
    éķ¿è¾¾
    -0.07
    æģ¤
    -0.06
    arium
    -0.06
    utan
    -0.06
    umer
    -0.06
    otta
    -0.06
    uto
    -0.06
    ç©
    -0.06
    POSITIVE LOGITS
    <Base
    0.07
    <![
    0.07
    emez
    0.07
    ÛĮÙĩ
    0.07
    emouth
    0.07
    表çİ°çļĦ
    0.07
    AINS
    0.07
    zia
    0.07
    ä¸įè¨Ģ
    0.07
    isans
    0.07
    Activations Density 0.275%

    No Known Activations