© 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. 16335
    Prev
    Next
    INDEX
    Explanations

    past time 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
    udre
    -0.07
    lead
    -0.07
    udier
    -0.06
    èı²åĪ©æĻ®
    -0.06
    inc
    -0.06
     ind
    -0.06
    edm
    -0.06
    mois
    -0.06
    udas
    -0.06
    antal
    -0.06
    POSITIVE LOGITS
     originally
    0.24
    åİŁåħĪ
    0.24
    åİŁæľ¬çļĦ
    0.23
    åİŁæľ¬æĺ¯
    0.23
    åİŁæľ¬
    0.22
    åİŁæĿ¥
    0.21
    åİŁæĿ¥çļĦ
    0.21
     previously
    0.21
    åİŁæľī
    0.20
     Originally
    0.20
    Activations Density 0.256%

    No Known Activations