© 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. 61406
    Prev
    Next
    INDEX
    Explanations

    US/JP patent 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
    çĪĽ
    -0.07
    æľŁåĨħ
    -0.07
    Ùĭ
    -0.06
    åĸĿçļĦ
    -0.06
    çĥĤ
    -0.06
    éri
    -0.06
     hind
    -0.06
    ose
    -0.06
    ä¾Ŀæīĺ
    -0.06
     Rod
    -0.06
    POSITIVE LOGITS
    ahun
    0.08
    antine
    0.08
    _reporting
    0.08
    ÃŃa
    0.08
    apas
    0.07
    ernels
    0.07
    arus
    0.07
     menyar
    0.07
    该åIJį
    0.07
    arne
    0.07
    Activations Density 0.017%

    No Known Activations