© 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. 51648
    Prev
    Next
    INDEX
    Explanations

    working assumptions

    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
    åĩŃåĢŁåħ¶
    -0.07
     Neuer
    -0.07
    å£ķ
    -0.07
    鼨åIJİ
    -0.07
    ventional
    -0.06
    伺
    -0.06
    orris
    -0.06
    alli
    -0.06
    utkan
    -0.06
    çĿ£
    -0.06
    POSITIVE LOGITS
     assumptions
    0.12
     assumption
    0.11
     assumed
    0.10
     assumes
    0.09
     Assumes
    0.08
    åģĩ设
    0.08
     assume
    0.08
    éĢīæĭ©åIJĪéĢĤçļĦ
    0.08
     충ë¶ĦíŀĪ
    0.08
     assum
    0.07
    Activations Density 0.005%

    No Known Activations