© 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. 49983
    Prev
    Next
    INDEX
    Explanations

    annealing

    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
    aret
    -0.07
    ota
    -0.07
    ÙĪعات
    -0.07
    arer
    -0.06
     sé
    -0.06
    خر
    -0.06
    çada
    -0.06
    HING
    -0.06
     Haley
    -0.06
     Indah
    -0.06
    POSITIVE LOGITS
    icast
    0.08
    ovac
    0.07
    issan
    0.07
    arge
    0.07
    oid
    0.07
    avage
    0.07
    planation
    0.07
    .unpack
    0.07
    elit
    0.07
    ighb
    0.07
    Activations Density 0.002%

    No Known Activations