© 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. 50601
    Prev
    Next
    INDEX
    Explanations

    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
     Studie
    -0.07
    è¡Ĺä¸Ĭ
    -0.07
    mpz
    -0.07
    å±±ä¸Ĭ
    -0.07
    æĺ¯çľŁçļĦ
    -0.07
    ÙĤدر
    -0.07
    ])-
    -0.07
     membr
    -0.06
    tiers
    -0.06
     cyl
    -0.06
    POSITIVE LOGITS
    è§
    0.07
    .Dot
    0.07
    夸
    0.07
    avin
    0.07
    çĸij
    0.07
    agra
    0.07
     Tart
    0.06
     Schönheit
    0.06
     Seymour
    0.06
    BaseContext
    0.06
    Activations Density 0.002%

    No Known Activations