© 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. 20807
    Prev
    Next
    INDEX
    Explanations

    url paths and file 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
    ooth
    -0.08
    ay
    -0.08
    oom
    -0.07
    eer
    -0.07
    eira
    -0.06
     =
    -0.06
    æĹıçļĦ
    -0.06
    ande
    -0.06
     "=",
    -0.06
    ollow
    -0.06
    POSITIVE LOGITS
    å°Ķçī¹
    0.08
    umbing
    0.08
    æİĪæĿĥçļĦ
    0.08
    zex
    0.07
    بس
    0.07
    .responses
    0.07
     amie
    0.07
    BitFields
    0.07
    éķ¿æľŁä»İäºĭ
    0.07
    åİŁä»¶åıĬ
    0.07
    Activations Density 0.118%

    No Known Activations