© 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. 42873
    Prev
    Next
    INDEX
    Explanations

    prime factors or division

    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
     Donner
    -0.07
    bite
    -0.06
     per
    -0.06
    ira
    -0.06
    殿
    -0.06
    baum
    -0.06
     by
    -0.06
     Sus
    -0.06
     Perk
    -0.06
     spre
    -0.06
    POSITIVE LOGITS
    nte
    0.08
    stantiate
    0.08
    heed
    0.08
    ocop
    0.07
    seud
    0.07
    isans
    0.07
    ä¸įèĥľ
    0.07
    ä¸Ńå¿ĥçŃī
    0.07
    IBUTE
    0.07
    çĩķå±±
    0.07
    Activations Density 0.002%

    No Known Activations